Current conversational AI systems based on large language models (LLMs) are known to generate unsafe responses, agreeing to offensive user input or including toxic content. Previous research aimed to alleviate the toxicity, by fine-tuning LLM with manually annotated safe dialogue histories. However, the dependency on additional tuning requires substantial costs. To remove the dependency, we propose GrounDial, where response safety is achieved by grounding responses to commonsense social rules without requiring fine-tuning. A hybrid approach of in-context learning and human-norm-guided decoding of GrounDial enables the response to be quantitatively and qualitatively safer even without additional data or tuning.
SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；University of Liverpool（利物浦大学）；City University of Hong Kong（香港城市大学）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）；China Mobile Research Institute（中国移动研究院）；China Mobile (Suzhou) Software Technology Co., Ltd（中国移动苏州软件技术有限公司）
DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents
Curai Health（Curai健康）
大语言模型（LLM）已经成为许多自然语言理解任务的有价值的工具。在医疗保健等安全关键型应用中，这些模型的实用性取决于它们生成真实准确和完整的输出的能力。在这项工作中，我们提出了对话使能解析代理（DERA）。DERA是一个范例，通过LLM的会话能力的增加而成为可能，即GPT-4。它为模型提供了一个简单的、可解释的论坛，以交流反馈并迭代地改进输出。我们框架我们的对话作为两个代理类型之间的讨论-一个研究员，谁处理信息，并确定关键的问题组件，和一个决策者，谁拥有自主权，以整合研究员的信息，并作出判断的最终输出。我们测试DERA对三个临床重点任务。对于医疗会话摘要和护理计划生成，DERA在人类专家偏好评估和定量指标方面都显示出比基本GPT-4性能的显着改进。在一项新的发现中，我们还表明，GPT-4在MedQA问答（QA）数据集（Jin et al. 2021，USMLE）的开放式版本上的性能（70%）远高于及格水平（60%），DERA表现出类似的性能。我们在https://github.com/curai/curai-research/tree/main/DERA上发布开放式MEDQA数据集。
Conversation AI Dialog for Medicare powered by Finetuning and Retrieval Augmented Generation
University of Florida（佛罗里达大学）；National Institute of Technology Calicut（卡利卡特国家理工学院）；SRM, Chennai（SRM大学（金奈））；University of Cincinnati（辛辛那提大学）；Dartmouth College（达特茅斯学院）；Arizona State University（亚利桑那州立大学）
TAF-MED: Multi-Turn Safety Refusal Collapse in LLMs Under Declared Self-Treatment Intent
Independent Researcher（独立研究者）；School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）；Institute of General Practice, Faculty of Medicine and Medical Center, University of Freiburg（弗莱堡大学医学中心医学院普通实践研究所）
DialogGuard: Multi-Agent Psychosocial Safety Evaluation of Sensitive LLM Responses
University of Leeds（利兹大学）；Southwest Jiaotong University（西南交通大学）；Department of Industrial Engineering and Management（工业工程与管理系）；Ben-Gurion University of the Negev（贝内尔·加隆大学）
