9 papers
ExpRL: Exploratory RL for LLM Mid-Training
Violet Xiang, Amrith Setlur, Chase Blagden +2
Sparse reward reinforcement learning (RL) has become a standard tool for improving LLM reasoning, but its success depends critically on the coverage present in the base model. In p…
One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models
Daniel Fein, Max Lamparth, Violet Xiang +2
Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences. However, RM-based preference-tuning is vulnerable to reward hacking, whereby L…
Data-efficient pre-training by scaling synthetic megadocs
Konwoo Kim, Suhas Kotha, Yejin Choi +3
Synthetic data augmentation has emerged as a promising solution when pre-training is constrained by data rather than compute. We study how to design synthetic data algorithms that…
LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing
Daniel Fein, Sebastian Russo, Violet Xiang +3
Evaluating creative writing generated by large language models (LLMs) remains challenging because open-ended narratives lack ground truths. Without performant automated evaluation…
Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning
Violet Xiang, Chase Blagden, Rafael Rafailov +4
Large reasoning models (LRMs) achieve higher performance on challenging reasoning tasks by generating more tokens at inference time, but this verbosity often wastes computation on…
ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code
Tianyu Hua, Harper Hua, Violet Xiang +5
Large language models (LLMs) have shown promise in transforming machine learning research, yet their capability to faithfully implement novel ideas from recent research papers-idea…