5 citations · 7 across the 13 of their papers we have counts for
18 papers
Rubric Judgments Lack Uncertainty: Conformal Weighting for LLM Evaluation
Licheng Pan, Haocheng Yang, Haoxuan Li +7
Rubric-based evaluation is widely used to assess large language model (LLM) outputs by decomposing quality into multiple criteria and assigning each a binary judgment from an LLM v…
Mitigating Cross-Modal Hallucinations by Correcting Modality Misrouting in Omnimodal LLMs
Yu Mi, Licheng Pan, Jiayi Zhu +7
Omnimodal large language models (OLLMs) are susceptible to cross-modal hallucinations under audio-visual interference. We find that, for a substantial fraction of incorrect joint p…
CollageAttack: Exploiting Cross-Modal Alignment Flaws in T2I Models through Spatial Text Composition
Zhiyi Mou, Yao Lu, Wangze Ni +6
Text-to-image (T2I) models have substantially improved in language understanding, in-image text rendering, and visual composition, while their safety mechanisms do not always keep…
DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models
Qirui Liu, Yichen Sun, Yan Wang +4
Safety alignment of large reasoning models (LRMs) via supervised fine-tuning (SFT) and reinforcement learning (RL) often yields near-perfect safety scores, yet this apparent succes…
EOPSA: Efficient On-Policy Self-Distilled Safety Alignment
Qirui Liu, Yichen Sun, Yan Wang +5
On-Policy Self-Distillation (OPSD) has emerged as a promising paradigm for safety alignment, delivering dense, token-level supervision by distilling from a teacher conditioned on r…
Beyond Final Decisions: A Process-Centric Benchmark for Transparent AI-Assisted Peer Review
Siming Yuan, Xueyi Zhang, Wangze Ni +7
Peer review is central to quality control in science. However, existing evaluations of AI-assisted peer review mainly focus on the overall quality of generated reviews or the accur…
From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs
Zhiyi Mou, Wangze Ni, Tianfang Xiao +6
LLMs are increasingly deployed in real-world applications, making inference efficiency and service reliability critical concerns due to their substantial computational costs. Howev…
EHR-Complex: Benchmarking Medical Agents for Complex Clinical Reasoning
Yitong Qiao, Lei Liu, Yue Shen +4
Clinical agents promise to democratize access to electronic health records (EHRs), yet existing benchmarks fail to reflect the complexity of practical EHR analysis, e.g., often ope…
QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving
Jianxin Yan, Wangze Ni, Zhenxin Li +8
Retrieval-augmented generation (RAG) improves large language model (LLM) answer quality by grounding generation in external evidence, but processing retrieved contexts makes the pr…
ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
Yan Wang, Zhixuan Chu, Zihao Xue +9
Reasoning-based LLM guardrails improve safety moderation by generating explicit rationales before issuing final decisions. However, their rationales do not always lead to faithful…
SRBench: A Comprehensive Benchmark for Sequential Recommendation with Large Language Models
Jianhong Li, Zeheng Qian, Wangze Ni +4
LLM development has aroused great interest in Sequential Recommendation (SR) applications. However, comprehensive evaluation of SR models remains lacking due to the limitations of…
RAC: Relation-Aware Cache Replacement for Large Language Models
Yuchong Wu, Zihuan Xu, Wangze Ni +5
The scaling of Large Language Model (LLM) services faces significant cost and latency challenges, making effective caching under tight capacity crucial. Existing cache replacement…
A Causal Perspective for Enhancing Jailbreak Attack and Defense
Licheng Pan, Yunsheng Lu, Jiexi Liu +5
Uncovering the mechanisms behind "jailbreaks" in large language models (LLMs) is crucial for enhancing their safety and reliability, yet these mechanisms remain poorly understood.…
Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training
Lei Liu, Hao Zhu, Yue Shen +4
Continual Pre-training (CPT) serves as a fundamental approach for adapting foundation models to domain-specific applications. Scaling laws for pre-training define a power-law relat…
Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework
Zhenjie Xu, Wenqing Chen, Yi Tang +6
Natural language processing (NLP) has seen remarkable advancements with the development of large language models (LLMs). Despite these advancements, LLMs often produce socially bia…
JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit
Zeqing He, Zhibo Wang, Zhixuan Chu +4
Despite the outstanding performance of Large language Models (LLMs) in diverse tasks, they are vulnerable to jailbreak attacks, wherein adversarial prompts are crafted to bypass th…
Towards Real-world Debiasing: Rethinking Evaluation, Challenge, and Solution
Peng Kuang, Zhibo Wang, Zhixuan Chu +2
Spurious correlations in training data significantly hinder the generalization capability of machine learning models when faced with distribution shifts, leading to the proposition…
S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
Xiaohan Yuan, Jinfeng Li, Dongxia Wang +9
Generative large language models (LLMs) have revolutionized natural language processing with their transformative and emergent capabilities. However, recent evidence indicates that…