3 citations · 5 across the 28 of their papers we have counts for
10 papers · 1 filter
Is Imagination Derived from Hallucination? A Cross-Taxonomy Evaluation of Imagination and Hallucination in Large Language Models
Zixuan Tang, Hongzong Li, Shuxin Zhuang +2
Imagination performs as a high-level function of large language models (LLMs) which determines the potential of how an LLM creates unseen or creative content. While existing works…
Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality
Qipeng Xie, Zi Liang, Jiafei Wu +6
Large Language Models (LLMs) exhibit extreme sensitivity to surface-level prompt variations, in which minor lexical changes can trigger disproportionate performance fluctuations. M…
FIT to Forget: Robust Continual Unlearning for Large Language Models
Xiaoyu Xu, Minxin Du, Kun Fang +5
While large language models (LLMs) exhibit remarkable capabilities, they increasingly face demands to unlearn memorized privacy-sensitive, copyrighted, or harmful content. Existing…
From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
Xiaoyu Xu, Minxin Du, Zitong Li +6
Although machine unlearning is essential for removing private, harmful, or copyrighted content from LLMs, current benchmarks often fail to faithfully represent the true ``forgettin…
How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework
Zi Liang, Liantong Yu, Shiyu Zhang +2
Overestimation in evaluating large language models (LLMs) has become an increasing concern. Due to the contamination of public benchmarks or imbalanced model training, LLMs may ach…
How Vital is the Jurisprudential Relevance: Law Article Intervened Legal Case Retrieval and Matching
Nuo Xu, Pinghui Wang, Zi Liang +2
Legal case retrieval (LCR) aims to automatically scour for comparable legal cases based on a given query, which is crucial for offering relevant precedents to support the judgment…
Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models
Zi Liang, Haibo Hu, Qingqing Ye +2
The drastic increase of large language models' (LLMs) parameters has led to a new research direction of fine-tuning-free downstream customization by prompts, i.e., task description…
Healing Unsafe Dialogue Responses with Weak Supervision Signals
Zi Liang, Pinghui Wang, Ruofei Zhang +3
Recent years have seen increasing concerns about the unsafe response generation of large-scale dialogue systems, where agents will learn offensive or biased behaviors from the real…
MERGE: Fast Private Text Generation
Zi Liang, Pinghui Wang, Ruofei Zhang +3
The drastic increase in language models' parameters has led to a new trend of deploying models in cloud servers, raising growing concerns about private inference for Transformer-ba…
Multi-Action Dialog Policy Learning from Logged User Feedback
Shuo Zhang, Junzhou Zhao, Pinghui Wang +5
Multi-action dialog policy, which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient sys…