1 citations · 1 across the 7 of their papers we have counts for
6 papers · 1 filter
Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text
Chengyu Huang, Sheng-Yen Chou, Zhengxin Zhang +1
Self-play has recently emerged as a promising paradigm for post-training Large Language Models (LLMs). In self-play, the target LLM creates the task input (e.g., a question), which…
Token-weighted Direct Preference Optimization with Attention
Chengyu Huang, Zhuohang Li, Sheng-Yen Chou +1
Direct Preference Optimization (DPO) aligns Large Language Models with human preferences without the need for a separate reward model. However, DPO treats all tokens in responses e…
Judging with Confidence: Calibrating Autoraters to Preference Distributions
Zhuohang Li, Xiaowei Li, Chengyu Huang +11
The alignment of large language models (LLMs) with human values increasingly relies on using other LLMs as automated judges, or ``autoraters''. However, their reliability is limite…
DCRM: A Heuristic to Measure Response Pair Quality in Preference Optimization
Chengyu Huang, Tanya Goyal
Recent research has attempted to associate preference optimization (PO) performance with the underlying preference datasets. In this work, our observation is that the differences b…
HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization
Chengyu Huang, Zhengxin Zhang, Claire Cardie
While scaling the length of responses at test-time has been shown to markedly improve the reasoning abilities and performance of large language models (LLMs), it often results in v…
Inherent limitations of LLMs regarding spatial information
He Yan, Xinyao Hu, Xiangpeng Wan +3
Despite the significant advancements in natural language processing capabilities demonstrated by large language models such as ChatGPT, their proficiency in comprehending and proce…