3 citations · 6 across the 13 of their papers we have counts for
9 papers · 1 filter
SagaQA: A Multi-hop Reasoning Benchmark for Long-form Narrative Understanding in TV Series
Galann Pennec, Zhengyuan Liu, Nicholas Asher +2
We introduce SagaQA, a long-form video benchmark for multi-hop reasoning over full-length TV series. Existing video reasoning benchmarks often emphasize local understanding of adja…
The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation
Herun Wan, Jiaying Wu, Minnan Luo +4
Multi-agent LLM systems often treat consensus as evidence of successful interaction. For deliberative problems, however, reliability depends on whether agents preserve the facts an…
MeMo: Memory as a Model
Ryan Wei Heng Quek, Sanghyuk Lee, Alfred Wei Lun Leong +6
Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Many real-world applications req…
What Makes a Good Natural Language Prompt?
Do Xuan Long, Duy Dinh, Ngoc-Hai Nguyen +4
As large language models (LLMs) have progressed towards more human-like and human--AI communications have become prevalent, prompting has emerged as a decisive component. However,…
Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines
Do Xuan Long, Duong Ngoc Yen, Do Xuan Trong +5
In-context learning (ICL) is an important yet not fully understood ability of pre-trained large language models (LLMs). It can greatly enhance task performance using a few examples…
Preference Optimization for Reasoning with Pseudo Feedback
Fangkai Jiao, Geyang Guo, Xingxing Zhang +3
Preference optimization techniques, such as Direct Preference Optimization (DPO), are frequently employed to enhance the reasoning capabilities of large language models (LLMs) in d…
Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models
Do Xuan Long, Duong Ngoc Yen, Anh Tuan Luu +3
We present Multi-expert Prompting, a novel enhancement of ExpertPrompting (Xu et al., 2023), designed to improve the large language model (LLM) generation. Specifically, it guides…
LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs
Do Xuan Long, Hai Nguyen Ngoc, Tiviatis Sim +5
We present the first systematic evaluation examining format bias in performance of large language models (LLMs). Our approach distinguishes between two categories of an evaluation…
Aligning Large Language Models with Human Opinions through Persona Selection and Value--Belief--Norm Reasoning
Do Xuan Long, Kenji Kawaguchi, Min-Yen Kan +1
Reasoning and predicting human opinions with large language models (LLMs) is essential yet challenging. Current methods employ role-playing with personae but face two major issues:…