2 citations · 3 across the 11 of their papers we have counts for
8 papers · 1 filter
DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment
Tianzhuo Yang, Shaoheng Yan, Lin Lu +5
Safety alignment teaches language models to refuse harmful requests, yet the internal accessibility of hazardous concepts can retain traces of earlier training. Can checkpoints wit…
HGP:An on-device personalized agent memory via hybrid graph storage
Ran Zhou, Xueming Han, Jiaheng Liu +4
LLM-based agents face challenges in personalized interactive tasks due to heterogeneous, multi-typed, and implicitly constrained long-term traces. Existing memory mechanisms strugg…
EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval
Huiqi Miao, Xinbao Sun, Bo Wang +6
Enterprise RAG deployments face a critical reliability gap: while LLMs satisfy 80% of individual constraints, only 26.8% of responses meet all requirements simultaneously, revealin…
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
Jiaming Wang, Ziteng Feng, Jiangtao Wu +8
Deep-research agents solve tasks through long trajectories of search, tool use, evidence inspection, and answer synthesis. Evaluation based on final answers shows whether an agent…
JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data
Junlan Feng, Fanyu Meng, Chong Long +12
We introduce JT-Safe-V2, a large language model designed to advance the safety and trustworthiness of foundation models, extending our previous JT-Safe model toward a more comprehe…
Strategy-Aware Optimization Modeling with Reasoning LLMs
Ruiqing Zhao, Fengzhi Li, Yuan Zuo +5
Large language models (LLMs) can generate syntactically valid optimization programs, yet often struggle to reliably choose an effective modeling strategy, leading to incorrect form…
Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
Siyuan Gan, Jiaheng Liu, Boyan Wang +8
Large reasoning models (LRMs) have attracted much attention due to their exceptional performance. However, their performance mainly stems from thinking, a long Chain of Thought (Co…
Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning
Taihang Zhen, Jialiang Hong, Kai Chen +12
Large reasoning models (LRMs) often exhibit overthinking, producing verbose Chain-of-Thought (CoT) traces that increase inference cost and obscure the underlying reasoning process.…