12 citations · 101 across the 80 of their papers we have counts for
8 papers · 1 filter
Understanding and Mitigating Hallucination Escape in Tool-Using LLM Agents
Peigui Qi, Kunsheng Tang, Yide Song +2
Large language models (LLMs) increasingly serve as autonomous agents that invoke external tools. However, this capability introduces tool hallucination, selecting incorrect tools o…
GlitchPatch: Repairing Glitch Tokens in Frozen Language Models via Local Retokenization
Kunsheng Tang, Peigui Qi, Yide Song +3
Glitch tokens are anomalous vocabulary entries that can cause large language models (LLMs) to produce outputs inconsistent with their inputs. Existing repair methods require access…
Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
Yanghao Su, Wenbo Zhou, Tianwei Zhang +4
Emergent Misalignment refers to a failure mode in which fine-tuning large language models (LLMs) on narrowly scoped data induces broadly misaligned behavior. Prior explanations mai…
MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG
Pingyu Wu, Daiheng Gao, Jing Tang +4
Retrieval-Augmented Generation (RAG) improves Large Language Models (LLMs) by using external knowledge, but it struggles with precise entity information retrieval. In this paper, w…
GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models
Kunsheng Tang, Wenbo Zhou, Jie Zhang +7
Large language models (LLMs) have exhibited remarkable capabilities in natural language generation, but they have also been observed to magnify societal biases, particularly those…
Towards Generalist Prompting for Large Language Models by Mental Models
Haoxiang Guan, Jiyan He, Shuxin Zheng +3
Large language models (LLMs) have demonstrated impressive performance on many tasks. However, to achieve optimal performance, specially designed prompting methods are still needed.…
Watermarking Text Generated by Black-Box Language Models
Xi Yang, Kejiang Chen, Weiming Zhang +5
LLMs now exhibit human-like skills in various fields, leading to worries about misuse. Thus, detecting generated text is crucial. However, passive detection methods are stuck in do…
DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection
Xiao Yu, Yuang Qi, Kejiang Chen +6
Large language models (LLMs) have the potential to generate texts that pose risks of misuse, such as plagiarism, planting fake reviews on e-commerce platforms, or creating inflamma…