52 papers
HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs
Ru Peng, Tianyu Zhao, Xijun Gu +9
The paper introduces HSS-Synth, a pipeline that creates high‑quality instruction‑tuning data for large language models in the humanities and social sciences by generating seed docu…
BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences
Ru Peng, Haokai Xu, Xijun Gu +11
BridgeAlign introduces a three-stage pipeline that creates and uses synthetic preference data to align large language models with nuanced quality judgments in humanities and social…
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
Yucheng Li, Huiqiang Jiang, Yang Xu +14
Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-To…
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
Bowen Wang, Dunjie Lu, Junli Wang +11
Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agents…
MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation
Xiaoyuan Li, Keqin Bao, Yubo Ma +6
Recent advances in Large Language Models (LLMs) have shown promising results in complex reasoning tasks. However, current evaluations predominantly focus on single-turn reasoning s…
Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective
Liyuan Mao, Le Yu, Jing Zhou +7
In this work, we reveal that Large Language Models (LLMs) possess intrinsic behavioral plasticity-akin to chameleons adapting their coloration to environmental cues-that can be exp…