4 papers
Uncovering Factor Level Preferences to Improve Human-Model Alignment
Juhyun Oh, Eunsu Kim, Jiseon Kim +4
Large language models (LLMs) often exhibit tendencies that diverge from human preferences, such as favoring certain writing styles or producing overly verbose outputs. While crucia…
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
Wenda Xu, Rujun Han, Zifeng Wang +7
Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised…
LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback
Wenda Xu, Daniel Deutsch, Mara Finkelstein +6
Recent large language models (LLM) are leveraging human feedback to improve their generation quality. However, human feedback is costly to obtain, especially during inference. In t…
BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment
Wenda Xu, Jiachen Li, William Yang Wang +1
Direct alignment from preferences (DAP) has emerged as a promising paradigm for aligning large language models (LLMs) to human desiderata from pre-collected, offline preference dat…