5 papers
Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization
Hongli Zhou, Hui Huang, Rui Zhang +5
Large language model (LLM)-based judges are widely adopted for automated evaluation and reward modeling, yet their judgments are often affected by judgment biases. Accurately evalu…
Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory
Hongli Zhou, Hui Huang, Ziqing Zhao +10
The evaluation of large language models (LLMs) via benchmarks is widespread, yet inconsistencies between different leaderboards and poor separability among top models raise concern…
MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training
Hui Huang, Jiaheng Liu, Yancheng He +5
Complex instruction-following with elaborate constraints is imperative for Large Language Models (LLMs). While existing methods have constructed data for complex instruction alignm…
An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4
Hui Huang, Xingyuan Bu, Hongli Zhou +5
Recently, there has been a growing trend of utilizing Large Language Model (LLM) to evaluate the quality of other LLMs. Many studies have fine-tuned judge models based on open-sour…
PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment
Dongxu Liu, Bing Xu, Yinzhuo Chen +4
Reinforcement Learning from Human Feedback (RLHF) has been proven to be an effective method for preference alignment of large language models (LLMs) and is widely used in the post-…