Large Language Models (LLMs) have achieved exceptional capabilities in open generation across various domains, yet they encounter difficulties with tasks that require intensive knowledge. To address these challenges, methods for integrating knowledge have been developed, which augment LLMs with domain-specific knowledge graphs through external modules. These approaches, however, face data inefficiency issues as they necessitate the processing of both known and unknown knowledge for fine-tuning. Thus, our research focuses on a novel problem: efficiently integrating unknown knowledge into LLMs without unnecessary overlap of known knowledge. A risk of introducing new knowledge is the potential forgetting of existing knowledge. To mitigate this risk, we propose the innovative {\method} framework. This framework employs transformer internal states to determine when to enrich LLM outputs with additional information, effectively preventing knowledge forgetting. Performance evaluations using the UMLS-2.5k and MetaQA domain knowledge graphs reveal that {\method} not only successfully integrates new knowledge but also outperforms state-of-the-art baselines, reducing knowledge forgetting by 9\% and 6\%, respectively.
Yale University（耶鲁大学）；Stanford University（斯坦福大学）；University of Chicago（芝加哥大学）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）；University of California, San Diego（圣地亚哥大学）
Enhancing LLM Reasoning with Reward-guided Tree Search
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；School of Information, Renmin University of China（中国人民大学信息学院）；BAAI（北京智源人工智能研究院）；Baichuan AI（百川智能）
WaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache Filtering
Nanjing University of Science and Technology（南京理工大学）；Alibaba Group（阿里巴巴集团）；Huzhou Normal University（湖州师范学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Enhancing Adversarial Transferability by Balancing Exploration and Exploitation with Gradient-Guided Sampling
School of Computer Science & Software Engineering, Shenzhen University, China（深圳大学计算机科学与软件工程学院）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China（广东省人工智能与数字经济发展实验室（深圳））；Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen University, China（广东省智能信息处理省级重点实验室）；School of Computer Science, University of Exeter, U.K.（埃克塞特大学计算机科学学院）；Department of Computing and Information Technology, Great Bay University, China（大鹏大学计算与信息技术系）；Computer Vision Institute, School of Artificial Intelligence, Shenzhen University, China（人工智能学院计算机视觉研究所）
TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning
Tsinghua University（清华大学）；Nanyang Technological University（南洋理工大学）；Princeton University（普林斯顿大学）；Shanghai AI Lab（上海人工智能实验室）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
Enhancing Geo-localization for Crowdsourced Flood Imagery via LLM-Guided Attention
Department of Urban Planning and Design, The University of Hong Kong（香港大学城市规划与设计系）；Urban Systems Institute, The University of Hong Kong（香港大学都市系统研究所）；Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology（香港理工大学土木与环境工程系）
Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China（认知智能国家重点实验室，中国科学技术大学）；Artificial Intelligence Research Institute, iFLYTEK Co., Ltd（iFLYTEK公司人工智能研究院）
SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning
The State Key Laboratory of Blockchain and Data Security（区块链与数据安全国家重点实验室）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院）；Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系）；School of Computer Science, Beijing University of Posts and Telecommunications（北京邮电大学计算机学院）
Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision
School of Computer Science, University of Sheffield（谢菲尔德大学计算机科学学院）；School of Electronic Engineering and Computer Science, Queen Mary University of London（伦敦大学玛丽女王学院电子工程与计算机科学学院）；The Alan Turing Institute（艾伦·图灵研究所）
Legal$Δ$: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain
School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）；Department of Computer Science and Technology, Institute for AI, Tsinghua University（清华大学人工智能研究院计算机科学与技术系）；Microsoft Research Asia（微软亚洲研究院）
Enhancing Target-Guided Proactive Dialogue Systems via Conversational Scenario Modeling and Intent-Keyword Bridging
School of Computer Science and Technology, Soochow University, China（苏州大学计算机科学与技术学院）；Jiangsu Key Lab of Language Computing, Suzhou（江苏省语言计算重点实验室）；School of Computer and Information Engineering, Henan Normal University, China（河南师范大学计算机与信息工程学院）
GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
Southern University of Science and Technology（南方科技大学）；Alibaba Group（阿里巴巴集团）；Shanghai University of Finance and Economics（上海财经大学）；Tsinghua University（清华大学）；Xiamen University（厦门大学）
Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding
The Hong Kong Polytechnic University（香港理工大学）；IROOTECH TECHNOLOGY（IROOTECH技术公司）；Wolf 1069 b Lab, Sany Group（三一集团沃尔夫1069实验室）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Zhejiang University（浙江大学）
Prompt as Free Lunch: Enhancing Diversity in Source-Free Cross-domain Few-shot Learning through Semantic-Guided Prompting
College of Computer and Data Science, Fuzhou University（福州大学计算机与数据科学学院）；Zhejiang University of Technology（浙江工业大学）；Hangzhou International Innovation Institute, Beihang University（北京航空航天大学杭州国际创新研究院）；INSAIT, Sofia University（保加利亚索菲亚大学INSAIT研究院）
Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS
Chongqing University（重庆大学）；Queen Mary University of London（伦敦玛丽女王大学）；Chongqing Key Laboratory of Big Data Intelligence and Privacy Computing（重庆市大数据智能与隐私计算重点实验室）；Fangda Partners（方达律师事务所）
