Papers

Agent

• [ICLR 2023]ReAct: Synergizing Reasoning and Acting in Language Models 2023.03

• [NIPS 2023]Reflexion: Language Agents with Verbal Reinforcement Learning 2023.03

• [NeurIPS 2023] CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society 2023.03

• [ICLR 2024] AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors 2023.08

• [ICLR 2024] MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework 2023.08

• [ICLR 2024] AgentTuning: Enabling Generalized Agent Abilities for LLMs 2023.09

• [arxiv] FireAct: Toward Language Agent Fine-tuning 2023.09

• [arxiv] MAGDI: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models 2024.02

• [arxiv] RECONCILE: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs 2024.02

• [arxiv] AUTOACT: Automatic Agent Learning from Scratch via Self-Planning 2024.02

Knowledge Edit

• [ICLR 2024] Unveiling the Pitfalls of Knowledge Editing for Large Language Models 2023.10
• [AAAI 2024] Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons 2023.08
• [AAAI 2024] ProAgent: Building Proactive Cooperative Agents with Large Language Models 2023.08
• [ACL 2023] Can We Edit Factual Knowledge by In-Context Learning? 2023.05
• [ICML 2022] Memory-Based Model Editing at Scale(SERAC) 2022.06
• [NeurIPS 2022] Locating and Editing Factual Associations in GPT(ROME) 2022.02
• [arxiv] MQUAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions 2023.05
• [arxiv] PokeMQA: Programmable knowledge editing for Multi-hop Question Answering 2023.12
• [arxiv] Multi-hop Question Answering under Temporal Knowledge Editing(TEMPLE-MQA) 2024.04

Knowledge + LLM

• [ICLR 2024] Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models 2023.05

Knowledge Fusion

• [ICLR 2024] Knowledge Fusion of Large Language Models 2024.01
• [arxiv] Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch 2024.02
• [NIPS 2023] TIES-Merging: Resolving Interference When Merging Models 2023.08
• [arxiv] Merging Models with Fisher-Weighted Averaging 2022.08

Graph+LLM

• [arxiv] GraphGPT: Graph Instruction Tuning for Large Language Models 2023.10
• [arxiv] Graphllm: Boosting graph reasoning ability of large language model 2023.10
• [WWW 2024] GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks 2024.02

Multimodal hallucination

• [ICML 2024] HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding 2024.05
• [CVPR 2024] Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding 2023.11