Papers by Zhi-Yuan Chen
Large Language Model-based Human-Agent Collaboration for Complex Task Solving (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in large language models have led to the development of LLM-based autonomous agents. |
| Approach: | They propose a Reinforcement Learning-based Human-Agent Collaboration method which trains a policy model to determine the most opportune stages for human intervention within the task-solving process. |
| Outcome: | The proposed method improves human-agent collaboration significantly through well-planned, limited human intervention. |
Beyond the Surface: Measuring Self-Preference in LLM Judgments (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods measure self-preference bias by comparing the scores a judge model assigns to its own responses with those assigned to other models. |
| Approach: | They propose to use gold judgments as proxies for the actual quality of responses . they propose to measure self-preference bias as the difference between the judge model's own and other models' scores . |
| Outcome: | The proposed method can assess self-preference bias across large language models . it uses gold judgments as proxies for the ground truth scores of the judge model . |
Towards Tool Use Alignment of Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on tool use with LLMs focus on enhancing tool-calling ability of LLM . e.g., LLM should not answer unsafe tool use relevant instructions or insecure tool responses to ensure reliability and harmlessness. |
| Approach: | They propose to use supervised fine-tuning and preference learning to align LLMs with H2A principle for tool use. |
| Outcome: | The proposed model demonstrates that LLMs can generate truthful and helpful responses while remaining harmless. |
Towards Preference Following in Tool Calling Language Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Currently, large language model (LLM)-based agents can't follow user preferences when calling tools. |
| Approach: | They propose a benchmark to evaluate agents' ability to identify personalized user preferences from interaction histories and to adhere to these preferences when calling tools. |
| Outcome: | The proposed model achieves 51.16% accuracy on the APOLLO benchmark, while GPT-4o achieves only 51.13% accuracy. |