Web IR NLP Group @ NUS
Web IR NLP Group @ NUS
Tour
News
People
Events
Gallery
Publications
Projects
Contact
Light
Dark
Automatic
Paper-Conference
LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs
A systematic evaluation of output-format bias in LLMs, with prompting and fine-tuning strategies for reducing format sensitivity.
Xuan Long Do
,
Hai N. Nguyen
,
Tiviatis Sim
,
Hieu Dao
,
Shafiq Joty
,
Kenji Kawaguchi
,
Nancy F. Chen
,
Min-Yen Kan
PDF
Cite
Aligning Large Language Models with Human Opinions through Persona Selection and Value-Belief-Norm Reasoning
Chain-of-Opinion selects and reasons over explicit and implicit personae to improve LLM opinion prediction and alignment.
Xuan Long Do
,
Kenji Kawaguchi
,
Min-Yen Kan
,
Nancy F. Chen
Cite
URL
DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation
DnA-Eval decomposes and aggregates LLM-as-judge evaluation to improve interpretability and agreement with human preferences.
Minzhi Li (Ella)
,
Zhengyuan Liu
,
Shumin Deng
,
Shafiq Joty
,
Nancy F. Chen
,
Min-Yen Kan
Cite
URL
Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning
A NeurIPS 2024 workshop paper on boosting reasoning with MCTS-driven iterative preference learning.
Yuxi Xie
,
Anirudh Goyal
,
Wenyue Zheng
,
Min-Yen Kan
,
Timothy P. Lillicrap
,
Kenji Kawaguchi
,
Michael Qizhe Shieh
PDF
Cite
Code
OpenReview
arXiv
Multi-expert Prompting Improves Reliability, Safety and Usefulness of Large Language Models
An EMNLP 2024 prompting method that simulates and aggregates multiple expert responses to improve LLM reliability, safety, and usefulness.
Xuan Long Do
,
Duong Ngoc Yen
,
Anh Tuan Luu
,
Kenji Kawaguchi
,
Min-Yen Kan
,
Nancy F. Chen
PDF
Cite
Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models
An EMNLP 2024 study of adversarial suffix transfer learning on aligned large language models.
Hongfu Liu
,
Yuxi Xie
,
Ye Wang
,
Michael Qizhe Shieh
PDF
Cite
Code
DOI
ACL Anthology
DataTales: A Benchmark for Real-World Intelligent Data Narration
An EMNLP 2024 benchmark of 4.9k financial reports and market data for evaluating data narration by language models.
Yajing Yang
,
Qian Liu
,
Min-Yen Kan
PDF
Cite
Code
Project
DOI
URL
MVP-Bench: Can Large Vision-Language Models Conduct Multi-level Visual Perception Like Humans?
A Findings of EMNLP 2024 benchmark for multi-level visual perception in large vision-language models.
Guanzhen Li
,
Yuxi Xie
,
Min-Yen Kan
PDF
Cite
Code
Dataset
DOI
ACL Anthology
Reasoning Robustness of LLMs to Adversarial Typographical Errors
An EMNLP 2024 study showing that adversarial typos can substantially degrade LLM reasoning and introducing the R2ATA robustness benchmark.
Esther Gan
,
Yiran Zhao
,
Liying Cheng
,
Mao Yancan
,
Anirudh Goyal
,
Kenji Kawaguchi
,
Min-Yen Kan
,
Michael Qizhe Shieh
PDF
Cite
Project
DOI
V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
A Findings of EMNLP 2024 method for mitigating hallucination in large vision language models.
Yuxi Xie
,
Guanzhen Li
,
Xiao Xu
,
Min-Yen Kan
PDF
Cite
Code
DOI
ACL Anthology
«
»
Cite
×