Current Large Language Models (LLMs) face inherent limitations due to their pre-defined context lengths, which impede their capacity for multi-hop reasoning within extensive textual contexts. While existing techniques like Retrieval-Augmented Generation (RAG) have attempted to bridge this gap by sourcing external information, they fall short when direct answers are not readily available. We introduce a novel approach that re-imagines information retrieval through dynamic in-context editing, inspired by recent breakthroughs in knowledge editing. By treating lengthy contexts as malleable external knowledge, our method interactively gathers and integrates relevant information, thereby enabling LLMs to perform sophisticated reasoning steps. Experimental results demonstrate that our method effectively empowers context-limited LLMs, such as Llama2, to engage in multi-hop reasoning with improved performance, which outperforms state-of-the-art context window extrapolation methods and even compares favorably to more advanced commercial long-context models. Our interactive method not only enhances reasoning capabilities but also mitigates the associated training and computational costs, making it a pragmatic solution for enhancing LLMs' reasoning within expansive contexts.
MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts
City University of Hong Kong（香港城市大学）；Harvard Medical School（哈佛医学院）；Institute of Automation, CAS（中国科学院自动化研究所）；Columbia University（哥伦比亚大学）；Ohio State University（俄亥俄州立大学）；Westlake University（西湖大学）；Nanjing University（南京大学）
University of Cambridge（剑桥大学）；Tencent AI Lab（腾讯人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）
The ability of a dialog system to express prespecified language style during conversations has a direct, positive impact on its usability and on user satisfaction. We introduce a new prototype-to-style (PS) framework to tackle the challenge of stylistic dialogue generation. The framework uses an Information Retrieval (IR) system and extracts a response prototype from the retrieved response. A stylistic response generator then takes the prototype and the desired language style as model input to obtain a high-quality and stylistic response. To effectively train the proposed model, we propose a n…
ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback
Mila-Québec Artificial Intelligence Institute（米拉-魁北克人工智能研究所）；Arizona State University（亚利桑那州立大学）；Princeton University（普林斯顿大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Université de Montréal（蒙特利尔大学）；National Research Council Canada（加拿大国家研究委员会）
LLMs Meet Multimodal Generation and Editing: A Survey
The Hong Kong University of Science and Technology（香港科技大学）；The Chinese University of Hong Kong（香港中文大学）；Tsinghua University（清华大学）；Tencent AI Lab（腾讯AI实验室）
Even the largest neural networks make errors, and once-correct predictions can become invalid as the world changes. Model editors make local updates to the behavior of base (pre-trained) models to inject updated knowledge or correct undesirable behaviors. Existing model editors have shown promise, but also suffer from insufficient expressiveness: they struggle to accurately model an edit's intended scope (examples affected by the edit), leading to inaccurate predictions for test inputs loosely related to the edit, and they often fail altogether after many edits. As a higher-capacity alternativ…
Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition
State Key Laboratory for Novel Software Technology, Nanjing University, China（新型软件技术国家重点实验室，南京大学，中国）；National Institute of Healthcare Data Science, Nanjing University, China（医疗数据科学国家研究院，南京大学，中国）
MILA - Quebec AI Institute（MILA - 魁北克人工智能研究所）；Microsoft（微软公司）；UNC Chapel Hill（北卡罗来纳大学教堂山分校）；North Carolina State University（北卡罗来纳州立大学）；Massachusetts Institute of Technology（麻省理工学院）；Google DeepMind（谷歌DeepMind）
Context-Robust Knowledge Editing for Language Models
Graduate School of Data Science, Seoul National University（首尔国立大学数据科学研究生院）；School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology（全州科学技术院电子工程与计算机科学学院）
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）
Scenario-based question answering (SQA) requires retrieving and reading paragraphs from a large corpus to answer a question which is contextualized by a long scenario description. Since a scenario contains both keyphrases for retrieval and much noise, retrieval for SQA is extremely difficult. Moreover, it can hardly be supervised due to the lack of relevance labels of paragraphs for SQA. To meet the challenge, in this paper we propose a joint retriever-reader model called JEEVES where the retriever is implicitly supervised only using QA labels via a novel word weighting mechanism. JEEVES signi…
NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database
Department of Mathematical Sciences, Tsinghua University（清华大学数学科学系）；IIIS, Tsinghua University（清华大学人工智能学院）；College of AI, Tsinghua University（清华大学人工智能学院）；Huawei Technologies Co., Ltd.（华为技术有限公司）
Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval Augmented Generation Across Learning Style
RespAI Lab, KIIT Bhubaneswar（KIIT布巴内斯瓦尔 RespAI 实验室）；BITS Pilani（皮拉尼比尔拉理工学院）；University of South Florida（南佛罗里达大学）；Pennsylvania State University（宾夕法尼亚州立大学）
Multi-hop Question Answering under Temporal Knowledge Editing
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；South China University of Technology（华南理工大学）；Ant Group（蚂蚁集团）；SDAIA-KAUST AI（沙特数据与人工智能局-阿卜杜拉国王科技大学人工智能项目）；Provable Responsible AI and Data Analytics (PRADA) Lab（可信赖负责任人工智能与数据分析实验室）
TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment
Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbrücken, Germany（马克斯·普朗克研究所信息学院，萨尔兰信息学院，德国萨尔布吕肯）；Department of Language Science and Technology, Saarland University, Saarbrücken, Germany（语言科学与技术系，萨尔兰大学，德国萨尔布吕肯）
Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community
Tsinghua University（清华大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Huawei Technologies Ltd. Co（华为技术有限公司）；Jilin University（吉林大学）；Zhejiang University（浙江大学）；Shandong University（山东大学）；Shandong Artificial Intelligence Institute（山东人工智能研究院）；South China University of Technology（华南理工大学）；Renmin University of China（中国人民大学）；University of Science and Technology of China（中国科学技术大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Wuhan University（武汉大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shanxi University（山西大学）；Jiangxi Normal University（江西师范大学）；Hefei University of Technology（合肥工业大学）；Baidu Inc.（百度公司）；Tianjin University（天津大学）；Shanghai Jiao Tong University（上海交通大学）；Chongqing University of Technology（重庆理工大学）
