10 papers
RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution
Junjie Zhang, Hui Liu, Kecheng Chen +3
LLM-based agents are increasingly deployed in product-level execution harnesses, where jailbreaks can trigger harmful tool use and persistent state changes, creating greater risks…
Unbiased Alignment for Large Language Models with Noisy Preferences
Jialiang Wang, Xianming Liu, Xiong Zhou +2
The alignment of large language models with human preferences is commonly achieved through Reinforcement Learning from Human Feedback or Direct Preference Optimization. However, th…
Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models
Kecheng Chen, Ziru Liu, Xijia Tao +9
Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive language models, offering stronger global awareness and highly parallel generati…
Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
Xiaozhe Zhang, Chaozhuo Li, Hui Liu +4
Large language models remain vulnerable to adversarial prompts that elicit harmful outputs. Existing safety paradigms typically couple red-teaming and post-training in a closed, po…
Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios
Hui Liu, Bin Zou, Kecheng Chen +3
Large language models (LLMs) exhibit substantial variability in performance and computational cost across tasks and queries, motivating routing systems that select models to meet u…
Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition
Hui Liu, Kecheng Chen, Jialiang Wang +3
Vision-Language Models (VLMs), such as CLIP, have significantly advanced zero-shot image recognition. However, their performance remains limited by suboptimal prompt engineering an…
Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models
Kecheng Chen, Ziru Liu, Xijia Tao +7
Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on lo…
Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics
Yueqing Xi, Yifan Bai, Huasen Luo +3
As artificial intelligence permeates judicial forensics, ensuring the veracity and traceability of legal question answering (QA) has become critical. Conventional large language mo…
Domain-Specific Data Generation Framework for RAG Adaptation
Chris Xing Tian, Weihao Xie, Zhen Chen +5
Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning power of large language models (LLMs) with external retrieval to enable domain-grounded respo…
TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection
Hui Liu, Wenya Wang, Haoru Li +1
The proliferation of fake news has emerged as a severe societal problem, raising significant interest from industry and academia. While existing deep-learning based methods have ma…