4 papers
References Improve LLM Alignment in Non-Verifiable Domains
Kejian Shi, Yixin Liu, Peifeng Wang +3
While Reinforcement Learning with Verifiable Rewards (RLVR) has shown strong effectiveness in reasoning tasks, it cannot be directly applied to non-verifiable domains lacking groun…
PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning
Ruixiang Feng, Yuntao Wen, Silin Zhou +14
Language Reasoning Models (LRMs) achieve strong performance by scaling test-time computation but often suffer from ``overthinking'', producing excessively long reasoning traces tha…
SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature
David Wadden, Kejian Shi, Jacob Morrison +11
We present SciRIFF (Scientific Resource for Instruction-Following and Finetuning), a dataset of 137K instruction-following instances for training and evaluation, covering 54 tasks.…
MSRS: Evaluating Multi-Source Retrieval-Augmented Generation
Rohan Phanse, Yijie Zhou, Kejian Shi +4
Retrieval-augmented systems are typically evaluated in settings where information required to answer the query can be found within a single source or the answer is short-form or fa…