Large language models (LLMs) are initially trained on vast amounts of data, then fine-tuned using reinforcement learning from human feedback (RLHF); this also serves to teach the LLM to provide appropriate and safe responses. In this paper, we present a novel method to manipulate the fine-tuned version into reverting to its pre-RLHF behavior, effectively erasing the model's filters; the exploit currently works for GPT4, Claude Sonnet, and (to some extent) for Inflection-2.5. Unlike other jailbreaks (for example, the popular "Do Anything Now" (DAN) ), our method does not rely on instructing the LLM to override its RLHF policy; hence, simply modifying the RLHF process is unlikely to address it. Instead, we induce a hallucination involving reversed text during which the model reverts to a word bucket, effectively pausing the model's filter. We believe that our exploit presents a fundamental vulnerability in LLMs currently unaddressed, as well as an opportunity to better understand the inner workings of LLMs during hallucinations.
From Judgments to Issues: Structured Extraction of Legal Reasoning with Citation-Hallucination Control
Quantitative and Digital Law Laboratory（量化与数字法律实验室）；CIRSFID - Alma AI, Faculty of Law University of Bologna（CIRSFID - 阿尔玛AI，博洛尼亚大学法学院）；Robert Schuman Centre European University Institute（罗伯特·施曼中心欧洲大学研究所）
VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck
College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China（复旦大学计算机科学与人工智能学院，上海，中国）；Shanghai Key Laboratory of Intelligent Information Processing（上海智能信息处理重点实验室）
HalluScore: Large Language Model Hallucination Question Answering Benchmark
Department of Information and Computer Science, King Fahd University of Petroleum and Minerals（国王法赫德石油与矿物大学信息与计算机科学系）；SDAIA-KFUPM Joint Research Center for Artificial Intelligence（SDAIA-KFUPM人工智能联合研究中心）
Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
University of Science and Technology of China（中国科学技术大学）；Shanghai Advanced Research Institute, Chinese Academy of Sciences（上海先进研究院，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）
Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?
CISPA Helmholtz Center for Information Security（CISPA 欧洲信息安全中心）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Southern University of Science and Technology（南方科技大学）
Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts
Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Key Laboratory of AI Safety, Chinese Academy of Sciences（中国科学院人工智能安全重点实验室）
Hallucination as a Feature, not a Defect: Evaluating a multi-agent architecture to transform speculative language-model outputs into testable scientific hypotheses
Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval
Computational Unit, Z.H. College of Engineering & Technology, Aligarh Muslim University, India（计算单元，Z.H. 工程技术学院，阿利加尔穆斯林大学，印度）；Interdisciplinary Center for Artificial Intelligence, Aligarh Muslim University, India（跨学科人工智能中心，阿利加尔穆斯林大学，印度）；Department of Computer Engineering, Aligarh Muslim University, India（计算机工程系，阿利加尔穆斯林大学，印度）
Tackling the Inherent Difficulty of Noise Filtering in RAG
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院）；Beijing Key Laboratory of Big Data Management and Analysis Methods（北京大数据管理与分析方法重点实验室）；School of Software Tsinghua University（清华大学软件学院）
Efficient Epistemic Uncertainty Estimation for Large Language Models via Knowledge Distillation
Graduate School of Data Science, Seoul National University（首尔国立大学数据科学研究生院）；Department of Rural Systems Engineering, Seoul National University（首尔国立大学农村系统工程系）；Department of Aerospace Engineering, Seoul National University（首尔国立大学航空航天工程系）；Department of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology（全州科学科技研究院电子工程与计算机科学系）
SafeLLM: Extraction as a Hallucination-Resistant Alternative to Rewriting in Safety-Critical Settings
Institute of Health Informatics, University College London（伦敦大学学院健康信息学研究所）；National Hospital for Neurology and Neurosurgery（国家神经内科与神经外科医院）；Somerset NHS Foundation Trust（萨默塞特NHS基金会信托）；King's College Hospital（国王学院医院）；King's College London（伦敦国王学院）
