University of California, Los Angeles | November 17, 2023
Welcome
The SoCal NLP Symposium aims to bring together students and faculty to promote natural language processing research in the (Southern) California region. The 4th SoCal NLP Symposium will be held at Mong Learning Center, the ground floor of the Engineering VI building at UCLA, Los Angeles, CA.
We call for poster presentations by researchers, students, and postdocs that describe ongoing, planned, or completed research projects, including previously published results and negative results. Research in any field applying computational methods to any aspect of human language, from all areas of computer science, linguistics, engineering, neuroscience, social science, information science, and related fields, is welcome. All accepted submissions are non-archival (only paper title and authorship will be revealed in our website) and will be presented as posters.
Poster Reminder: The size of the poster board is 30" x 40". Please print your poster accordingly. We recommend printing a 24” x 36” poster in a vertical orientation.
If the paper is published in a recent conference or journal, you can directly submit the paper without modification. Please indicate where the paper is published in the Abstract when submitting the paper.
For papers that have not been previously published, we recommend submitting an extended summary spanning no more than two pages, formatted according to the ACL guidelines, However, submissions of a longer length will also be considered.
Parking information: The closest parking lot for visitors is located on the top floor of Parking Structure 8 (501 Westwood Plaza, Los Angeles, CA). It will cost $15 for a full day parking. You can pay the fee in pay station or pay-by-phone.
If Structure 8 is full, parking structures 2 and 18 are also within walking distance. The detailed information can be found here.
Title: Group Preference Optimization: Few-Shot Alignment of Large Language Models
Abstract: Many applications of large language models (LLMs), ranging from chatbots to creative writing, require nuanced subjective judgments that can differ significantly across different groups. Existing alignment algorithms can be expensive to align for each group, requiring prohibitive amounts of group-specific preference data and computation for real-world use cases. In this talk, I will introduce Group Preference Optimization (GPO), an alignment framework that steers language models to preferences of individual groups in a few-shot manner. In GPO, we augment the base LLM with an independent transformer module trained to predict the preferences of a group for the LLM generations. We empirically validate the efficacy of GPO through rigorous evaluations using LLMs with varied sizes on three human opinion adaptation tasks. These tasks involve adapting to the preferences of US demographic groups, global countries, and individual users. Our results demonstrate that GPO not only aligns models more accurately but also requires fewer group-specific preferences, and less training and inference computing resources, outperforming existing strategies such as in-context steering and fine-tuning methods. Towards the end of the talk, I will also highlight some surprising observations and open challenges with evaluating language models as a function of their feedback acquisition strategy.
Bio: Aditya Grover is an assistant professor of computer science at UCLA. His goal is to develop efficient machine learning approaches that can interact and reason with limited supervision. He grounds this research in applications in sustainability science. Aditya's research works have been published at top venues including Nature, deployed in production at major technology companies, and covered in popular press venues such as Wall Street Journal and Washington Post. His research has been recognized with a best paper award at NeurIPS, prominent graduate research fellowships and faculty awards (Adobe, Google, Meta, Microsoft, Sony, Simons Institute), the ACM SIGKDD Doctoral Dissertation Award, and the AI Researcher of the Year Award by Samsung, and the Kavli Fellowship from the US National Academy of Sciences. Aditya received his postdoctoral training at UC Berkeley, PhD at Stanford, and bachelors at IIT Delhi, all in computer science.
Diyi Yang
Title: Human-AI Interaction in the Age of LLMs
Abstract: Large language models have revolutionized the way humans interact with AI systems, transforming a wide range of fields and disciplines. In this talk, I share two distinct approaches to empowering human-AI interaction using LLMs. The first one explores how large language models transform computational social science, and how human-AI collaboration can reduce costs and improve the efficiency of social science research. The second part looks at social skill learning via LLMs by empowering therapists with LLM-empowered feedback and deliberative practices. These two works demonstrate how human-AI interaction via LLMs can empower individuals and foster positive change.
Bio: Diyi Yang is an assistant professor in the Computer Science Department at Stanford University. Her research focuses on natural language processing for social impact. She has received multiple best paper awards and recognitions at leading conferences in NLP and HCI. She is a recipient of IEEE AI 10 to Watch (2020), Intel Rising Star Faculty Award (2021), Microsoft Research Faculty Fellowship (2021), NSF CAREER Award (2022), and an ONR Young Investigator Award (2023).
Sean (Xiang) Ren
Title: Reflex or Reflect: When Do Language Tasks Need Slow Reasoning?
Abstract: Large language models, such as GPT-3, excel at generating reflexive responses that mimic human-like language, but they fall short when it comes to complex reasoning that requires slower thinking, deeper reflection and a nuanced interpretation of language. This talk will share two lines of efforts in approaching the above problem. In the first part, I will introduce RICA and RobustRL, two benchmarks that expose language models to logical robustness challenges in language inference. The second part presents our exploration on transferring the Chain-of-Thoughts ability to smaller language models while enhancing model’s logical consistency. We show that a smaller, distilled LM can yield dramatically better task accuracy and rationale-prediction consistency.
Bio: Sean Ren is an Associate Professor, Viterbi Early Career Chair, and Director of the INK Lab at the University of South California. He was previously a research scholar at Stanford and earned his Ph.D. from the University of Illinois Urbana-Champaign. Sean focuses on creating generalizable NLP systems to redefine human-AI collaboration. His research has received several Outstanding Paper Awards at the top AI conferences, an NSF CAREER Award, and research awards from Google, Meta, Amazon, JP Morgan, and Sony. Sean was named Forbes Asia 30 Under 30, and MIT Technology Review Innovators Under 35 (Asia Pacific).
Alane Suhr
Title: Continual Learning of Language Grounding from Situated Human-Agent Interactions
Abstract: Systems that use language in situated collaborative interactions with human users must reason about language as it is grounded in context. This includes grounding to visual perception and action, but also to the dynamics that arise in multi-turn interactions with human users, wherein users adapt their language and behavior to most effectively collaborate with an agent. While this interactive setting poses a significant challenge, it also opens up new learning opportunities, where a system can continually learn from its interactions with users as they mutually adapt to one another. In this talk, I will discuss a collaborative situated environment that supports studying human-agent language-based interactions, and approaches to continually improve language using agents through these interactions by taking advantage of feedback that is implicitly and explicitly available from these interactions.
Bio: Alane Suhr recently joined EECS and BAIR at UC Berkeley as an Assistant Professor. Alane's work focuses on building language-using systems that communicate with and learn from human users in collaborative, situated interactions. Prior to joining Berkeley, Alane completed a PhD in Computer Science at Cornell University / Cornell Tech and spent a year afterwards as a Young Investigator at the Allen Institute for AI.
Tatsunori Hashimoto
Title: Replicating and Auditing Black-Box Language Models
Abstract: Advances in large language models have brought about exciting advancements in capabilities, but the commercialization of this technology has led to an increasing loss of transparency. State-of-the-art language models effectively operate as black boxes, with many things unknown about their training algorithms, data annotators, and pertaining data.
I will cover a trio of recent works from my group that attempt to help us understand each of these components by replicating the RLHF training process (AlpacaFarm), probing LMs to identify whose opinions are being reflected in pretraining and RLHF data (OpinionQA), and providing provable guarantees of test set contamination in black-box language models.
Bio: Tatsunori Hashimoto is an Assistant Professor in the Computer Science Department at Stanford University. He is a member of the statistical machine learning and natural language processing groups at Stanford, and his research uses tools from statistics to make machine learning systems more robust and trustworthy — especially in complex systems such as large language models. He is a Kavli fellow, a Sony and Amazon research award winner, and his work has been recognized with best paper awards at ICML and CHI.
Before becoming an Assistant Professor, he was a postdoctoral researcher at Stanford with Percy Liang and John Duchi and received his Ph.D. from MIT under the supervision of Tommi Jaakkola and David Gifford.
Dan Roth
Title: LLMs that Reason and Orchestrate
Abstract: The rapid progress made over the last few years in generating linguistically coherent natural language has blurred, in the mind of many, the difference between natural language generation, understanding, and the ability to reason with respect to the world. Nevertheless, robust support of high-level decisions that depend on natural language understanding, and one that requires dealing with “truthfulness” are still beyond our capabilities, partly since most of these tasks are very sparse, often require grounding, and may depend on new types of supervision signals.
I will discuss some of the challenges underlying reasoning and argue that we should focus on LLMs as orchestrators – coordinating and managing multiple models, applications, and services, as a way to execute complex tasks and processes. I will discuss some of the challenges and present some of our work in this space, focusing on supporting task decomposition and planning.
Bio: Dan Roth is the Eduardo D. Glandt Distinguished Professor at the Department of Computer and Information Science, University of Pennsylvania, a VP/Distinguished Scientist at AWS AI Labs, and a Fellow of the AAAS, the ACM, AAAI, and the ACL.
In 2017 Roth was awarded the John McCarthy Award, the highest award the AI community gives to mid-career AI researchers. Roth was recognized “for major conceptual and theoretical advances in the modeling of natural language understanding, machine learning, and reasoning.”
Awards
Best Theme Paper on Trustworthy NLP presented by Capital One: Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language ModelsJailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models (UCR).
Best Published Paper presented by Amazon-UCLA Science Hub: ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool EmbeddingsShibo Hao, Tianyang Liu, Zhen Wang, Zhiting Hu (UCSD/MBZUAI).
Best Paper presented by SAP: Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear ModelsDeqing Fu, Tian-qi Chen, Robin Jia, Vatsal Sharan (USC).
Accepted Papers
Poster Session #1 (11:00am - 12:00pm)
FairGraph: Automated Graph Debiasing with Gradient Matching Yezi Liu
KPEval: Towards Fine-grained Semantic-based Evaluation of Keyphrase Extraction and Generation Systems Di Wu, Da Yin, Kai-Wei Chang
Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models Hritik Bansal, John Dang, Aditya Grover
Controllable Pareto Trade-off between Fairness and Accuracy Yongkang Du, Jieyu Zhao, Yijun Yang, Tianyi Zhou
Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond Haw-Shiuan Chang, Zonghai Yao, Alolika Gon, hong yu, Andrew McCallum
White-Box Multi-Objective Adversarial Attack on Dialogue Generation Yufei Li, Zexin Li, yingfan gao, Cong Liu
Uncertainty-Aware Bootstrap Learning for Joint Extraction on Distantly-Supervised Data Yufei Li, Xiao Yu, Yanchi Liu, Haifeng Chen, Cong Liu
ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation Yangyi Chen, Xingyao Wang, Manling Li, Derek Hoiem, Heng Ji
BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions Wenbo Hu
DOES VIDEO SUMMARIZATION REQUIRE VIDEOS? QUANTIFYING THE EFFECTIVENESS OF LANGUAGE IN VIDEO SUMMARIZATION Yoonsoo Nam, Adam Lehavi, Daniel Yang, Digbalay Bose, Swabha Swayamdipta, Shrikanth Narayanan
Open-world Semi-supervised Generalized Relation Discovery Aligned in a Real-world Setting William P Hogan, Jiacheng Li, Jingbo Shang
Exploring the Relationship Between Model Architecture and In-Context Learning Ability Ivan Lee, Nan Jiang, Taylor Berg-Kirkpatrick
How Should We Represent Dialog Acts to Leverage Pretrained Natural Language Generators? Alain Vazquez Risco, Asier Lopez Zorrilla, María Inés Torres Barañano
Interpretable Diffusion via Information Decomposition Xianghao Kong, Ollie Liu, Han Li, Dani Yogatama, Greg Ver Steeg
Zero-Shot Detection of Machine-Generated Codes Xianjun Yang, Kexun Zhang, Haifeng Chen, Linda Ruth Petzold, William Yang Wang, Wei Cheng
Harmful Speech Detection by Large Language Models Contains Gender-Queer Dialect Bias Rebecca Dorn, Lee Kezar, Negar Mokhberian, Fred Morstatter, Kristina Lerman
Automated Data Analysis Through Multi-Turn Code Generation Xueqing Wu, Rui Zheng, Nanyun Peng, Kai-Wei Chang, Haoran Huang
Robust Natural Language Understanding with Residual Attention Debiasing Fei Wang, James Y. Huang, Tianyi Yan, Wenxuan Zhou, Muhao Chen
Certified Robustness for Large Language Models with Self-Denoising Zhen Zhang, Bairu Hou
Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis Qiucheng Wu, Jiabao Ji
Language Models Meet World Models: Embodied Experiences Enhance Language Models Jiannan Xiang, Tianhua Tao, Yi Gu, Tianmin Shu, Zirui Wang, Zichao Yang, Zhiting Hu
The Bias Amplification Paradox in Text-to-Image Generation Preethi Seshadri, Sameer Singh, Yanai Elazar
Gender Biases in Automatic Evaluation Metrics for Image Captioning Haoyi Qiu, Zi-Yi Dou, Tianlu Wang, Asli Celikyilmaz, Nanyun Peng
A Causal View of Entity Bias in (Large) Language Models Fei Wang, Wenjie Mo, Yiwei Wang, Wenxuan Zhou, Muhao Chen
Intrepretability in Machine Translation Models with Controlled Generation capabilities Priyesh Vakharia, Ian Lane, Leilani H. Gilpin
Neural-symbolic Table Question Answering through Table Augmentation Yujian Liu
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition Ali Modarressi, Mohsen Fayyaz, Ehsan Aghazadeh, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar
I'm not Racist but…: Discovering Bias in the Internal Knowledge of Large Language Models Abel Salinas, Louis Penafiel, Robert McCormack, Fred Morstatter
Open-Domain Text Evaluation via Contrastive Distribution Methods Sidi Lu, Tianlu Wang, Asli Celikyilmaz, Nanyun Peng
Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation Da Yin, Xiao Liu, Fan Yin, Ming Zhong, Hritik Bansal, Jiawei Han, Kai-Wei Chang
PHOTOSWAP: Personalized Subject Swapping in Images Jing Gu, Yilin Wang, Nanxuan Zhao, Tsu-Jui Fu, Wei Xiong, Qing Liu, Zhifei Zhang, HE Zhang, Jianming Zhang, HyunJoon Jung, Xin Eric Wang
Event Linking with an Event-Centric View Zihan Xue, I-Hung Hsu, Nilay Pochhi, Sahil Bansal, Jayanth Srinivasa, Nanyun Peng
Continual Dialogue State Tracking via Example-Guided Question Answering Hyundong Justin Cho, Andrea Madotto, Zhaojiang Lin, Khyathi Chandu, Satwik Kottur, Jing Xu, Jonathan May, Chinnadhurai Sankar
Multilingual Language Models are not Multicultural: A Case Study in Emotion Shreya Havaldar
Context-aware Event Forecasting via Graph Disentanglement Yunshan Ma, Chenchen Ye, Zijian Wu, Xiang Wang, Yixin Cao, Tat-Seng Chua
Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering Wang Zhu, Jesse Thomason, Robin Jia
Challenges in Context-Aware Neural Machine Translation Linghao Jin, Jacqueline He, Jonathan May, Xuezhe Ma
SearchVQA: Visual Reasoning through Reliable VQA Use Tejas Srinivasan, Jack Hessel, Tanmay Gupta, Bill Yuchen Lin, Yejin Choi, Jesse Thomason, Khyathi Chandu
SCIBENCH: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models Xiaoxuan Wang, Ziniu Hu, Pan Lu, Yanqiao Zhu, Jieyu Zhang, Satyen Subramaniam, Arjun R Loomba, Shichang Zhang, Yizhou Sun, Wei Wang
Prompt Engineering a Prompt Engineer Qinyuan Ye, Mohamed Ahmed, Reid Pryzant, Fereshte Khani
LayoutGPT: Compositional Visual Planning and Generation with Large Language Models Weixi Feng, Wanrong Zhu, Tsu-Jui Fu, Varun Jampani, Arjun Reddy Akula, Xuehai He, S Basu, Xin Eric Wang, William Yang Wang
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin
Estimating Large Language Model Capabilities without Labeled Test Data Harvey Yiyun Fu, Qinyuan Ye, Albert Xu, Xiang Ren, Robin Jia
Text Alignment Is An Efficient Unified Model for Massive NLP Tasks Yuheng Zha, Yichi Yang, Ruichen Li, Zhiting Hu
Creating a Parallel Corpus for a Low-Resource, Indigenous Language: Muisca-to-Spanish Aryan Gulati, Leslie Moreno, Aditya Kumar, Abhinav Gupta
Large Language Models can Learn Rules Zhaocheng Zhu, Yuan Xue, Xinyun Chen, Denny Zhou, Jian Tang, Dale Schuurmans, Hanjun Dai
From Text to Tactic: Evaluating LLMs Playing the Game of Avalon Jonathan Light, Min Cai, Sheng Shen, Ziniu Hu
VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use Yonatan Bitton, Hritik Bansal, Jack Hessel, Rulin Shao, Wanrong Zhu, Anas Awadalla, Joshua P Gardner, Rohan Taori, Ludwig Schmidt
Temporal Knowledge Graph Forecasting Using In-Context Learning Dong-Ho Lee, Kian Ahrabian, Woojeong Jin, Fred Morstatter, Jay Pujara
Analyzing Norm Violations in Live-Stream Chat Jihyung Moon, Dong-Ho Lee, Hyundong Justin Cho, Woojeong Jin, Chan Young Park, Minwoo Kim, Jonathan May, Jay Pujara, Sungjoon Park
From Shortcuts to Triggers: Backdoor Defense with Denoised PoE Qin Liu, Fei Wang, Chaowei Xiao, Muhao Chen
Learn Your Tokens: Word-Pooled Tokenization for Language Modeling Avijit Thawani, Saurabh Ghanekar, Xiaoyuan Zhu, Jay Pujara
Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative XML Path Zilong Wang, Jingbo Shang
Can LLM Replace Stack Overflow? A Study on Robustness and Reliability of Large Language Model Code Generation Li Zhong, Zilong Wang
Selective Perception: Learning Concise State Descriptions for Language Model Actors Kolby Nottingham, Yasaman Razeghi, Kyungmin Kim, JB Lanier, Pierre Baldi, Roy Fox, Sameer Singh
Capturing Perspectives of Sparse Annotators in Subjective Learning Tasks Negar Mokhberian, Myrl G Marmarelis, Frederic Rene Hopp, Fred Morstatter, Kristina Lerman
Cross-lingual Continual Learning Meryem M'hamdi, Xiang Ren, Jonathan May
Effect of Geometry on Graph Neural Networks Xinyue Cui, Praveen Bandla, Rishi Sonthalia
ClinScope Corpus - Clinical Notes Annotated for Hedge and Negation Lisa Chen, Paea LePendu
ED-FAITH: Evaluating Dialogue Summarization on Faithfulness Sicong Huang, Asli Celikyilmaz, Haoran Li
Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models Wenxuan Wang, Wenxiang Jiao, Jingyuan Huang, Ruyi Dai, Jen-tse Huang, Zhaopeng Tu, Michael Lyu
A Data Fusion Framework for Multi-Domain Morality Learning Siyi Guo, Negar Mokhberian, Kristina Lerman
Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data Mozhdeh Gheini, Tatiana Likhomanenko, Matthias Sperber, Hendra Setiawan
A New Approach to Decomposing Uncertainty Tailored for Large Language Models Bairu Hou
BOOST: Harnessing Black-Box Control to Boost Commonsense in LMs’ Generation Yufei Tian, Felix Zhang, Nanyun Peng
ToolDec: Syntax Error-Free and Generalizable Tool Use for LLMs via Finite-State Decoding Kexun Zhang, Hongqiao Chen, Lei Li, William Yang Wang
MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models Deepak Nathani
Less than One-shot: Named Entity Recognition via Extremely Weak Supervision Letian Peng, Zihan Wang, Jingbo Shang
Automatic Evaluation of Question Under Discussion Discourse Parsers Ashima Suvarna, Xiao Liu, Tanmay Parekh, Kai-Wei Chang, Nanyun Peng
Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy Yu Fu, Deyi Xiong, Yue Dong
Inverse Reinforcement Learning for Text Summarization Yu Fu, Deyi Xiong, Yue Dong
OCTOPUS: Open-vocabulary Content Tracking and Object Placement Using Semantic Understanding in Mixed Reality Luke Yoffe, Aditya Sharma, Tobias Hollerer
Coverage-based Example Selection for In-Context Learning Shivanshu Gupta, Matt Gardner, Sameer Singh
Simple Temporal Adaptation to Changing Label Sets: Hashtag Prediction via Dense KNN Niloofar Mireshghallah, Nikolai Vogler, Junxian He, Omar Florez, Ahmed El-Kishky, Taylor Berg-Kirkpatrick
A Multimodal Benchmark of Speech, Gaze, and Sketches for Detecting Alzheimer's disease and related dementias Leticia Leonor Pinto Alva, Jesse Thomason, Maja Mataric, Leslie Moreno, Gwen Bradforth, Riley Ashford, Cecily Chung
Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought Vaishnavi Himakunthala, Andy Ouyang, Daniel Philip Rose, Ryan He, Alex Mei, Yujie Lu, Chinmay Sonar, Michael Saxon, William Yang Wang
LegalDiscourse: Interpreting When Laws Apply and Who They Affect Alexander Spangher, Te-Lin Wu, Zihan Xue, Mark Hansen, Nanyun Peng, Jonathan May
Tracking the Newsworthiness of Public Documents Alexander Spangher, Nicholas Diakopoulos, Nanyun Peng, Serdar Tumgoren, Ben Welsh, Emilio Ferrara, Jonathan May
Negotiation Agents with Interpretable Strategic Planning: Synergy of LLMs and Reinforcement Learning-Based Steering Ian Wu, Yu Rong, Kushal Chawla, Gale Lucas, Jonathan Gratch
BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models Rafal Dariusz Kocielnik, Shrimai Prabhumoye, Vivian L Zhang, Roy Luoyao Jiang, R. Michael Alvarez, Anima Anandkumar
Are models biased on text without gender-related language? Catarina G Belém, Preethi Seshadri, Yasaman Razeghi, Sameer Singh
Characterizing Attitudes Towards Homelessness on Social Media Jaspreet Ranjit, Rebecca Dorn, Olga Koumoundouros, Laura Petry, Eric Rice, Swabha Swayamdipta
Large Language Models Can Be Good Privacy Protection Learners Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng
SemStamp: A Semantic Watermark With Paraphrastic Robustness For Text Generation Abe Bohan Hou, Jingyu Zhang, Tianxing He, Yichen Wang, Yung-Sung Chuang, Hongwei Wang, Lingfeng Shen, Benjamin Van Durme, Daniel Khashabi, Yulia Tsvetkov
Privacy-Preserving Language Model Inference with Instance Obfuscation Yixiang Yao, Fei Wang, Srivatsan Ravi, Muhao Chen
How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench Qinyuan Ye, Harvey Yiyun Fu, Xiang Ren, Robin Jia
Have I been trained on? Supporting the right to opt-out of LLMs Ryan Wang, Johnny Wei, Robin Jia
LLM still cannot play like human! Challenges of LLM's strategic playing in a game environment Ziyi Liu, Pei Zhou, Jieyu Zhao
PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization Xinyuan Wang, Chenxi Li, Zhen Wang, Fan Bai, Haotian Luo, Jiayou Zhang, Nebojsa Jojic, Eric P. Xing, Zhiting Hu
Multilingual Conceptual Coverage in Text-to-Image Models Michael Saxon, William Yang Wang
NEUROFORMER: MULTIMODAL AND MULTITASK GENERATIVE PRETRAINING FOR BRAIN DATA Antonis Antoniades, Yiyi Yu, Joe S Canzano, William Yang Wang, Spencer Smith
Evaluating Mathematical Reasoning in Visual Contexts with MathVista: A Study of GPT-4V, Bard, and Other Models Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, Jianfeng Gao
Defining Success for Localization of Memorized Data in LLMs Ting-Yun Chang, Robin Jia, Jesse Thomason
“Kelly is a Warm Person, Joseph is a Role Model”: Gender Biases in LLM-Generated Reference Letters Yixin Wan, George Pu, Jiao Sun, Aparna Garimella, Kai-Wei Chang, Nanyun Peng
AGent: A Novel Pipeline for Automatically Creating Unanswerable Questions Son Quoc Tran, Gia-Huy Hoang Do, Phong Nguyen-Thuan Do, Matt Kretchmar, Xinya Du
Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Models Deqing Fu, Tian-qi Chen, Robin Jia, Vatsal Sharan
Poster Session #3 (3:20pm - 4:20pm)
Closing the Curious Case of Neural Text Degeneration Matthew Finlayson, John Hewitt, Alexander Koller, Swabha Swayamdipta, Ashish Sabharwal
Error Detection on Knowledge Graphs with Triple Embedding Yezi Liu, Qinggang Zhang, Mengnan Du, Xiao Huang, Xia Hu
Exploring Distributional Shifts in Large Language Models for Code Analysis Shushan Arakelyan, Rocktim Jyoti Das, Yi Mao, Xiang Ren
Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data Alon Albalak, Colin Raffel, William Yang Wang
A Study on Linearizing Structured Data: Insights from Text-to-SQL Yutong Shao, Ndapa Nakashole
How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model Michael Hanna, Ollie Liu, Alexandre VariengienShow details
AVIS: Autonomous Visual Information Seeking with Large Language Model Agent Ziniu Hu
Will the Prince Get True Love’s Kiss? On the Model Sensitivity to Gender Perturbation over Fairytale Texts Christina A Chance, Da Yin, Dakuo Wang, Kai-Wei Chang
The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models Son Quoc Tran, Phong Nguyen-Thuan Do, Uyen Le, Matt Kretchmar
Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models Erfan Shayegani, Yue Dong, Nael Abu-Ghazaleh
SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples Deqing Fu, Ameya Godbole, Robin Jia
Alt-Text with Context: Improving Accessibility for Images on Twitter Nikita Srivatsan, Sofia Samaniego, Omar Florez, Taylor Berg-Kirkpatrick
Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge Te-Lin Wu, Yu Zhou, Nanyun Peng
Domain-specific Medical Vision-Language Pre-Training: A Dataset for Brain Diseases Masoud Monajatipoor, Zi-Yi Dou, Aichi Chien, Nanyun Peng, Kai-Wei Chang
Backtracking Mathematical Reasoning of Language Models to the Pretraining Data Yasaman Razeghi, Hamish Ivison, Sameer Singh, Yanai Elazar
CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation Minzhi Li, Taiwei Shi, Caleb Ziems, Min-Yen Kan, Nancy F. Chen, Zhengyuan Liu, Diyi Yang
MISGENDERED: Limits of Large Language Models in Understanding Tamanna Hossain, Sunipa Dev, Sameer Singh
Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models Pan Lu, Baolin Peng, Hao Cheng, Michel Galley, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, Jianfeng Gao
Look-back Decoding for Open-Ended Text Generation Nan Xu, Chunting Zhou, Asli Celikyilmaz, Xuezhe Ma
Mitigating Label Biases for In-context Learning Yu Fei, Yifan Hou, Zeming Chen, Antoine Bosselut
Exploring Training Objectives for Passage-level Differentiable Search Indexing Man Luo
Red Teaming Language Model Detectors with Language Models Zhouxing Shi, Yihan Wang, Fan Yin, Xiangning Chen, Kai-Wei Chang, Cho-Jui Hsieh
Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation Models Yiyuan Li, Rakesh R Menon, Sayan Ghosh, Shashank Srivastava
UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition Wenxuan Zhou, Sheng Zhang, Yu Gu, Muhao Chen, Hoifung Poon
Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks Po-Nien Kung, Fan Yin, Di Wu, Kai-Wei Chang, Nanyun Peng
R2H: Building Multimodal Navigation Helpers that Respond to Help Requests Yue Fan, Jing Gu, Kaizhi Zheng, Xin Eric Wang
Expanding the Study of Bias in Sentiment Analysis: Investigating Intersectionality and Cross-Linguistic Biases Casandra Rusti, Omneya Sultan
ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation Kaiwen Zhou, Kaizhi Zheng, Connor Pryor, Yilin Shen, Hongxia Jin, Lise Getoor, Xin Eric Wang
Estimating Causal Effects of Text Interventions Myrl G Marmarelis, Siyi Guo, Fred Morstatter, Kristina Lerman
Accelerating Diffusion Models for Zero-Shot Classification Xuehai He, Xin Eric Wang
Making Large Language Models Better Data Creators Dong-Ho Lee, Jay Pujara, Mohit Sewak, Ryen W White, Sujay Kumar Jauhar
Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models Alfonso Amayuelas
CausalDialogue: Modeling Utterance-level Causality in Conversations Yi-Lin Tuan, Alon Albalak, Wenda Xu, Michael Saxon, Connor Pryor, Lise Getoor, William Yang Wang
DesCo: Learning Object Recognition with Rich Language Descriptions Liunian Harold Li, Zi-Yi Dou, Nanyun Peng, Kai-Wei Chang
Does LLM reasoning support prediction? A case study on self-contradictory reasoning Ziyi Liu, Yongkang Du, Isabelle Lee, Soumya Sanyal, Jieyu Zhao
STAR: Improving Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models Mingyu Derek Ma, Xiaoxuan Wang, Po-Nien Kung, P. Jeffrey Brantingham, Nanyun Peng, Wei Wang
Lumos: Towards Language Agents that are Unified, Modular, and Open Source Da Yin, Faeze Brahman, Abhilasha Ravichander, Khyathi Chandu, Kai-Wei Chang, Yejin Choi, Bill Yuchen Lin
Leveraging Code to Improve In-Context Learning for Semantic Parsing Ben Bogin, Shivanshu Gupta, Peter Clark, Ashish Sabharwal
LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following Cheng-Fu Yang, Kai-Wei Chang
Reasoning with language model is planning with world model Shibo Hao, Yi Gu, Haodi Ma, Joshua Jiahua Hong, Zhen Wang, Daisy Zhe Wang, Zhiting Hu
Leveraging LLMs for Enhancing User Understanding of Privacy Policies Yubo Zhang, Jieyu Zhao
Fast Sampling via De-randomization for Discrete Diffusion Models Zixiang Chen, Huizhuo Yuan, Yongqian Li, Yiwen Kou, Junkai Zhang, Quanquan Gu
How FaR are Large Language Models from Agents with Theory-of-Mind? Pei Zhou, Aman Madaan, Srividya Pranavi Potharaju, Aditya Gupta, Kevin R. McKee, Ari Holtzman, Jay Pujara, Xiang Ren, Swaroop Mishra, Aida Nematzadeh, Shyam Upadhyay, Manaal Faruqui
ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings Shibo Hao, Tianyang Liu, Zhen Wang, Zhiting Hu
Are LLMs Effective Negotiators? Evaluating the Multifaceted Capabilities of LLMs in Negotiation Dialogues Kushal Chawla, Deuksin Kwon, Emily Weiss, Tara Kulshrestha, Gale Lucas, Jonathan Gratch
Large Language Models Are Not Robust Multiple Choice Selectors Chujie Zheng, Hao Zhou, Fandong Meng, Jie Zhou, Minlie Huang
EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning Raja Sekhar Reddy Mekala, Sameer Singh, Yasaman Razeghi
My MacGyver: Are Large Language Models Creative Problem Solvers? Yufei Tian, Abhilasha Ravichander, Lianhui Qin, Ronan Le Bras, Nanyun Peng, Yejin Choi, Thomas L. Griffiths, Faeze Brahman
Deriving Sign Language Phonemes with Neural Discrete Representation Learning Lee Kezar, Naomi Caselli, Jesse Thomason
Event Detection from Social Media for Epidemic Preparedness Tanmay Parekh, Anh Mac, Jiarui Yu, Yuxuan Dong, Syed Shahriar, Bonnie Liu, Eric J Yang, Kuan-Hao Huang, Nanyun Peng, Wei Wang, Kai-Wei Chang
