activity
20232025
collaborators

5 papers

cs.CL2025

On Evaluating LLM Alignment by Evaluating LLMs as Judges

Yixin Liu, Pengfei Liu, Arman Cohan

Alignment with human preferences is an important evaluation aspect of LLMs, requiring them to be helpful, honest, safe, and to precisely follow human instructions. Evaluating large…

cs.CL2024

Understanding Reference Policies in Direct Preference Optimization

Yixin Liu, Pengfei Liu, Arman Cohan

Direct Preference Optimization (DPO) has become a widely used training method for the instruction fine-tuning of large language models (LLMs). In this work, we explore an under-inv…

cs.CL2024

Evaluating Mathematical Reasoning Beyond Accuracy

Shijie Xia, Xuefeng Li, Yixin Liu +2

The leaderboard of Large Language Models (LLMs) in mathematical tasks has been continuously updated. However, the majority of evaluations focus solely on the final results, neglect…

cs.CL2024

Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate

Steffi Chern, Ethan Chern, Graham Neubig +1

Despite the utility of Large Language Models (LLMs) across a wide range of tasks and scenarios, developing a method for reliably evaluating LLMs across varied contexts continues to…

cs.CL2023

Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization

Yixin Liu, Alexander R. Fabbri, Jiawen Chen +7

While large language models (LLMs) can already achieve strong performance on standard generic summarization benchmarks, their performance on more complex summarization task setting…