zjunlp

[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction

Must-read Papers on LLM Agents.

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

Create, Evaluate, and Connect AI Skills

An Open-sourced Knowledgable Large Language Model Framework.

Must-read Papers on Knowledge Editing for Large Language Models.

[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

[ACL 2023] Reasoning with Language Model Prompting: A Survey

PromptKG Family: a Gallery of Prompt Learning & KG-related research works, toolkits, and paper-list.

[EMNLP 2025] OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

[WWWJ 2024] LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities

[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.

[EMNLP 2020] OpenUE: An Open Toolkit of Universal Extraction from Text

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

[ICLR 2024] Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models

[NAACL 2025] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents

[ACL 2024] AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning

[SIGIR 2022] Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion

[ACL 2024] IEPile: A Large-Scale Information Extraction Corpus

[WWW 2022] KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction

[WWW 2025] A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System.

[ICLR 2024] Domain-Agnostic Molecular Generation with Chemical Feedback

[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers

A Large-Scale Knowledge Graph for Automated Scientific Research

[NeurIPS 2024] Agent Planning with World Knowledge Model

[EMNLP 2025] LightThinker: Thinking Step-by-Step Compression

[IJCAI 2021] Document-level Relation Extraction as Semantic Segmentation

[ICLR 2025] Benchmarking Agentic Workflow Generation

[ICLR 2022] OntoProtein: Protein Pretraining With Gene Ontology Embedding

[ICLR/AAAI/KDD/EMNLP2026] Open-Source LLM-Based Data Analysis Agents

[ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

[EMNLP 2024] OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs.

[Neurocomputing 2023] Relational Graph Transformer for Knowledge Graph Representation

A Paper List of Low-resource Information Extraction

[ICLR 2023] Multimodal Analogical Reasoning over Knowledge Graphs

[ICLR 2022] Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

[NAACL 2022 Findings] Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction

[EMNLP 2026] LightMem-Ego: Your AI Memory for Everyday Life

[ACL 2024] Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View

[EMNLP 2022] Generative Knowledge Graph Construction: A Review

LabVLA: Grounding Vision–Language–Action Models in Scientific Laboratories

AutoMind: Adaptive Knowledgeable Agent for Automated Data Science

[ACL 2025] Agentic Knowledgeable Self-awareness

[IJCAI 2024] FactCHD: Benchmarking Fact-Conflicting Hallucination Detection

[EMNLP 2026] LightRSI is a modular runtime for lightly deploying recursive self-improvement loops in long-horizon LLM agents.

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

AI Systems as Scientific Instruments for Understanding the Mechanisms of Intelligence

ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark

[IJCAI 2024] Continual Multimodal Knowledge Graph Construction

Must-read papers on NLP for science.

[NLPCC 2023] Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings with Language Models

ChatCell: Facilitating Single-Cell Analysis with Natural Language

A Comprehensive Benchmarking Framework for Long-Term Conversational Memory Layers

[ACL 2025] How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training