21 citations · 64 across the 50 of their papers we have counts for
56 papers
ScopeIF: Improving Scope-Aware Precise Instruction-Following in Large Language Models via Graded Reward Modeling
Bosi Wen, Yilin Niu, Xiaoying Ning +3
Precise instruction-following is a fundamental ability of large language models (LLMs), requiring their outputs to strictly satisfy objective constraints in input instructions. In…
RUBAS: Rubric-Based Reinforcement Learning for Agent Safety
Xian Qi Loye, Qinglin Su, Zhexin Zhang +5
The evolution of LLMs into tool-enabled agents creates a new class of safety challenges associated with real-world execution rather than simple text generation. Existing alignment…
SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation
Junxiao Yang, Minghao Zhang, Xiaoce Wang +4
Recent generative models can now produce visual artifacts with realistic embedded text and layouts, creating a new misinformation threat: synthetic credibility. We introduce SYNCRE…
You Live More Than Once: Towards Hierarchical Skill Meta-Evolving
Xujun Li, Kehan Zheng, Mingyuan Zhao +7
Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric lea…
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
Junxiao Yang, Haoran Liu, Jinzhe Tu +9
Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried in low-resource languages. We a…
HoWToBench: Holistic Evaluation for LLM's Capability in Human-level Writing using Tree of Writing
Andrew Zhuoer Feng, Cunxiang Wang, Yu Luo +7
Evaluating the writing capabilities of large language models (LLMs) remains a significant challenge due to the multidimensional nature of writing skills and the limitations of exis…
IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation
Bosi Wen, Yilin Niu, Cunxiang Wang +5
Instruction-following is a foundational capability of large language models (LLMs), with its improvement hinging on scalable and accurate feedback from judge models. However, the r…
Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure
Yida Lu, Jianwei Fang, Xuyang Shao +7
As Large Language Models (LLMs) evolve from chatbots to agentic assistants, they are increasingly observed to exhibit risky behaviors when subjected to survival pressure, such as t…
RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models
Andrew Zhuoer Feng, Cunxiang Wang, Bosi Wen +4
Large language model alignment via reinforcement learning depends critically on reward function quality. However, static, domain-specific reward models are often costly to train an…
RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis
Andrew Zhuoer Feng, Cunxiang Wang, Yu Luo +9
Large Language Models have evolved from single-round generators into long-horizon agents, capable of complex text synthesis scenarios. However, current evaluation frameworks lack t…
Grounding LLMs in Scientific Discovery via Embodied Actions
Bo Zhang, Jinfeng Zhou, Yuxuan Chen +3
Large Language Models (LLMs) have shown significant potential in scientific discovery but struggle to bridge the gap between theoretical reasoning and verifiable physical simulatio…
The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond Deployment
Zhexin Zhang, Yida Lu, Junfeng Fang +8
Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training rem…
Trust-Region Adaptive Policy Optimization
Mingyu Su, Jian Guan, Yuxian Gu +2
Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning…
IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation
Bosi Wen, Yilin Niu, Cunxiang Wang +6
Instruction-following is a fundamental ability of Large Language Models (LLMs), requiring their generated outputs to follow multiple constraints imposed in input instructions. Nume…
Glyph: Scaling Context Windows via Visual-Text Compression
Jiale Cheng, Yusen Liu, Xinyu Zhang +11
Large language models (LLMs) increasingly rely on long-context modeling for tasks such as document understanding, code analysis, and multi-step reasoning. However, scaling context…
Data-Efficient RLVR via Off-Policy Influence Guidance
Erle Zhu, Dazhi Jiang, Yuan Wang +8
Data selection is a critical aspect of Reinforcement Learning with Verifiable Rewards (RLVR) for enhancing the reasoning capabilities of large language models (LLMs). Current data…
Think Socially via Cognitive Reasoning
Jinfeng Zhou, Zheyu Chen, Shuai Wang +4
LLMs trained for logical reasoning excel at step-by-step deduction to reach verifiable answers. However, this paradigm is ill-suited for navigating social situations, which induce…
Training Language Model to Critique for Better Refinement
Tianshu Yu, Chao Xiang, Mingchuan Yang +8
Large language models (LLMs) have demonstrated remarkable evaluation and critique capabilities, providing insightful feedback and identifying flaws in various tasks. However, limit…
ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs
Shiyao Cui, Qinglin Zhang, Xuan Ouyang +6
Toxicity detection in multimodal text-image content faces growing challenges, especially with multimodal implicit toxicity, where each modality appears benign on its own but convey…
Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
Zhexin Zhang, Yuhao Sun, Junxiao Yang +4
Fine-tuning on open-source Large Language Models (LLMs) with proprietary data is now a standard practice for downstream developers to obtain task-specific LLMs. Surprisingly, we re…
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
Zhexin Zhang, Xian Qi Loye, Victor Shea-Jay Huang +8
Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do n…
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
Junxiao Yang, Jinzhe Tu, Haoran Liu +9
Recent advances in Large Reasoning Models (LRMs) have shown impressive capabilities in mathematical and logical reasoning. However, current LRMs rarely admit ignorance or respond w…
Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialogues
Jinfeng Zhou, Yuxuan Chen, Jianing Yin +9
Cognitive Restructuring (CR) is a psychotherapeutic process aimed at identifying and restructuring an individual's negative thoughts, arising from mental health challenges, into mo…
StepMathAgent: A Step-Wise Agent for Evaluating Mathematical Processes through Tree-of-Error
Shu-Xun Yang, Cunxiang Wang, Yidong Wang +3
Evaluating mathematical capabilities is critical for assessing the overall performance of large language models (LLMs). However, existing evaluation methods often focus solely on f…