4 citations · 9 across the 13 of their papers we have counts for
15 papers
Curse of Knowledge: When Complex Evaluation Context Benefits yet Biases LLM Judges
Weiyuan Li, Xintao Wang, Siyu Yuan +5
As large language models (LLMs) grow more capable, they face increasingly diverse and complex tasks, making reliable evaluation challenging. The paradigm of LLMs as judges has emer…
ARIA: Training Language Agents with Intention-Driven Reward Aggregation
Ruihan Yang, Yikai Zhang, Aili Chen +5
Large language models (LLMs) have enabled agents to perform complex reasoning and decision-making through free-form language interactions. However, in open-ended language action en…
UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation
Ruihan Yang, Caiqi Zhang, Zhisong Zhang +4
Large Language Models (LLMs) are prone to hallucination, particularly in long-form generations. A promising direction to mitigate hallucination is to teach LLMs to express uncertai…
The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement
Ruihan Yang, Fanghua Ye, Jian Li +5
Large language models (LLMs) have recently transformed from text-based assistants to autonomous agents capable of planning, reasoning, and iteratively improving their actions. Whil…
Implicit Reasoning in Transformers is Reasoning through Shortcuts
Tianhe Lin, Jian Xie, Siyu Yuan +1
Test-time compute is emerging as a new paradigm for enhancing language models' complex multi-step reasoning capabilities, as demonstrated by the success of OpenAI's o1 and o3, as w…
Unlocking Scientific Concepts: How Effective Are LLM-Generated Analogies for Student Understanding and Classroom Practice?
Zekai Shao, Siyu Yuan, Lin Gao +3
Teaching scientific concepts is essential but challenging, and analogies help students connect new concepts to familiar ideas. Advancements in large language models (LLMs) enable g…
LoGU: Long-form Generation with Uncertainty Expressions
Ruihan Yang, Caiqi Zhang, Zhisong Zhang +5
While Large Language Models (LLMs) demonstrate impressive capabilities, they still struggle with generating factually incorrect content (i.e., hallucinations). A promising approach…
WAPITI: A Watermark for Finetuned Open-Source LLMs
Lingjie Chen, Ruizhong Qiu, Siyu Yuan +6
Watermarking of large language models (LLMs) generation embeds an imperceptible statistical pattern within texts, making it algorithmically detectable. Watermarking is a promising…
Past Meets Present: Creating Historical Analogy with Large Language Models
Nianqi Li, Siyu Yuan, Jiangjie Chen +5
Historical analogies, which compare known past events with contemporary but unfamiliar events, are important abilities that help people make decisions and understand the world. How…
SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals
Ruihan Yang, Jiangjie Chen, Yikai Zhang +5
Language agents powered by large language models (LLMs) are increasingly valuable as decision-making tools in domains such as gaming and programming. However, these agents often fa…
EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms
Siyu Yuan, Kaitao Song, Jiangjie Chen +3
The rise of powerful large language models (LLMs) has spurred a new trend in building LLM-based autonomous agents for solving complex tasks, especially multi-agent systems. Despite…
Boosting Scientific Concepts Understanding: Can Analogy from Teacher Models Empower Student Models?
Siyu Yuan, Cheng Jiayang, Lin Qiu +1
Analogical reasoning plays a critical role in human cognition, enabling us to understand new concepts by associating them with familiar ones. Previous research in the AI community…
"A good pun is its own reword": Can Large Language Models Understand Puns?
Zhijun Xu, Siyu Yuan, Lingjie Chen +1
Puns play a vital role in academic research due to their distinct structure and clear definition, which aid in the comprehensive analysis of linguistic humor. However, the understa…
Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works
Xinfeng Yuan, Siyu Yuan, Yuhan Cui +5
Large language models (LLMs) have demonstrated impressive performance and spurred numerous AI applications, in which role-playing agents (RPAs) are particularly popular, especially…
EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction
Siyu Yuan, Kaitao Song, Jiangjie Chen +5
To address intricate real-world tasks, there has been a rising interest in tool utilization in applications of large language models (LLMs). To develop LLM-based agents, it usually…