1 citations · 5 across the 24 of their papers we have counts for
29 papers
Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees
Wenbin Hu, Huihao Jing, Haochen Shi +9
Agent harnesses require a low-latency guardrail model together with customizable audit policies. However, deploying an auto-regressive guardrail model remains challenging: such mod…
RadixFlow: Filling Execution Bubbles in Prefix-Cached Hybrid LLM Serving
Huihao Jing, Wenbin Hu, Shaojin Chen +6
Prefix reuse improves LLM inference by sharing the KV cache of common prompt prefixes. This helps only if the scheduler can execute a matched branch in the current worker round. Sc…
Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization
Huihao Jing, Shaojin Chen, Wenbin Hu +5
As language-model agents write code, move money and change records on behalf of users, deciding whether an action is authorized has become a central safety problem. Guardrails are…
SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition
Yuxuan Liu, Zhaochen Su, Hangyu Guo +11
Long-horizon agents must complete workflows in which later activities depend on earlier outputs and changes to shared state. A key challenge for evaluation is to expand task requir…
SoFT: Soft Targets for Generalizable LLM Fine-Tuning
Huihao Jing, Wenbin Hu, Shaojin Chen +7
Distillation enables student language models to acquire new capabilities from expert teachers. However, integrating knowledge from multi-teacher, multi-domain demonstrations into a…
MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning
Kawai Chung, Chunkit Chan, Yauwai Yim +12
Multimodal Large Language Models have sparked significant interest due to their potential for social intelligence; however, their ability to perform sequential motivation reasoning…
Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos
Baixuan Xu, Yinyui Xu, Tianshi Zheng +9
While LVLMs rapidly improve, long-video question answering still remains challenging: relevant evidence is sparse, and question-relevant context often fails to provide cues that di…
RLPF: Reinforcement Learning from Performance Feedback for Code Generation
Huihao Jing, Haozhe Cui, Wenbin Hu +9
Code models are increasingly trained with execution feedback, but most training signals still stop at correctness. This leaves an important gap for systems code: two programs can p…
Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions
Huihao Jing, Wenbin Hu, Shaojin Chen +10
The capability of LLM agents to function as the ``brain'' of a system fundamentally expands the scope of analysis beyond a standalone model. Consequently, safety is no longer only…
PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization
Huihao Jing, Wenbin Hu, Shaojin Chen +5
Large language models (LLMs) can often generate functionally correct code, but their ability to produce efficient implementations for performance-critical systems tasks remains lim…
OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset
Wenbin Hu, Huihao Jing, Haochen Shi +3
Ensuring the safety and compliance of large language models (LLMs) is of paramount importance. However, existing LLM safety datasets often rely on ad-hoc taxonomies for data genera…
SurveyLens: A Discipline-Aware Benchmark for Automatic Survey Generation
Beichen Guo, Zhiyuan Wen, Jia Gu +6
Automatic Survey Generation (ASG) aims to produce comprehensive literature surveys by retrieving, organizing, and synthesizing academic papers. Despite rapid progress in specialize…
NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems
Jiayu Liu, Rui Wang, Qing Zong +9
Accurately assessing model confidence is essential for deploying large language models (LLMs) in mission-critical factual domains. While retrieval-augmented generation (RAG) is wid…
CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?
Qing Zong, Jiayu Liu, Tianshi Zheng +7
Accurate confidence calibration in Large Language Models (LLMs) is critical for safe use in high-stakes domains, where clear verbalized confidence enhances user trust. Traditional…
Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance
Wenbin Hu, Huihao Jing, Haochen Shi +2
The proliferation of Large Language Models (LLMs) has demonstrated remarkable capabilities, elevating the critical importance of LLM safety. However, existing safety methods rely o…
GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners
Haoran Li, Jingru Zeng, Yulin Chen +8
As large language models (LLMs) are integrated into numerous applications, LLMs' safety becomes critical for both application developers and intended users. Currently, great effort…
INFERENCEDYNAMICS: Efficient Routing Across LLMs through Structured Capability and Knowledge Profiling
Haochen Shi, Tianshi Zheng, Weiqi Wang +6
Large Language Model (LLM) routing is a pivotal technique for navigating a diverse landscape of LLMs, aiming to select the best-performing LLMs tailored to the domains of user quer…
Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study
Baixuan Xu, Chunyang Li, Weiqi Wang +6
Designing effective collaboration structure for multi-agent LLM systems to enhance collective reasoning is crucial yet remains under-explored. In this paper, we systematically inve…
The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning
Tianshi Zheng, Yixiang Chen, Chengxi Li +7
Chain-of-Thought (CoT) prompting has been widely recognized for its ability to enhance reasoning capabilities in large language models (LLMs). However, our study reveals a surprisi…
LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning
Tianshi Zheng, Jiayang Cheng, Chunyang Li +6
Modern large language models (LLMs) employ diverse logical inference mechanisms for reasoning, making the strategic optimization of these approaches critical for advancing their ca…
EcomEdit: An Automated E-commerce Knowledge Editing Framework for Enhanced Product and Purchase Intention Understanding
Ching Ming Samuel Lau, Weiqi Wang, Haochen Shi +3
Knowledge Editing (KE) aims to correct and update factual information in Large Language Models (LLMs) to ensure accuracy and relevance without computationally expensive fine-tuning…
ActPlan-1K: Benchmarking the Procedural Planning Ability of Visual Language Models in Household Activities
Ying Su, Zhan Ling, Haochen Shi +3
Large language models~(LLMs) have been adopted to process textual task description and accomplish procedural planning in embodied AI tasks because of their powerful reasoning abili…
On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions
Weiqi Wang, Tianqing Fang, Haochen Shi +8
Conceptualization, a fundamental element of human cognition, plays a pivotal role in human generalizable reasoning. Generally speaking, it refers to the process of sequentially abs…
MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding
Baixuan Xu, Weiqi Wang, Haochen Shi +12
Improving user experience and providing personalized search results in E-commerce platforms heavily rely on understanding purchase intention. However, existing methods for acquirin…