mlsanityData to 7 Oct 2026

InternLM2 Technical Report

arXiv 2403.17297 ↗First posted 26 Mar 2024cs.CL cs.AIcited by 391

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

Abstract (arXiv)

The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI). However, replicating such advancements in open-source models has been challenging. This paper introduces InternLM2, an open-source LLM that outperforms its predecessors in comprehensive evaluations across 6 dimensions and 30 benchmarks, long-context modeling, and open-ended subjective evaluations through innovative pre-training and optimization techniques. The pre-training process of InternLM2 is meticulously detailed, highlighting the preparation of diverse data types including text, code, and long-context data. InternLM2 efficiently captures long-term dependencies, initially trained on 4k tokens before advancing to 32k tokens in pre-training and fine-tuning stages, exhibiting remarkable performance on the 200k ``Needle-in-a-Haystack" test. InternLM2 is further aligned using Supervised Fine-Tuning (SFT) and a novel Conditional Online Reinforcement Learning from Human Feedback (COOL RLHF) strategy that addresses conflicting human preferences and reward hacking. By releasing InternLM2 models in different training stages and model sizes, we provide the community with insights into the model's evolution.

Key facts. Cited by 391 papers in the map (data through 7 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. First posted on arXiv 26 Mar 2024.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 128; 2025: 175; 2026: 88.

391 papers.

Sort:

By area:

  1. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  2. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  3. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,033
  4. 2025Visual-RFT: Visual Reinforcement Fine-Tuningcited by 501
  5. 2024From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipelinecited by 484
  6. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  7. 2024Skywork-Reward: Bag of Tricks for Reward Modeling in LLMscited by 322
  8. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Modelscited by 297
  9. 2024OLMoE: Open Mixture-of-Experts Language Modelscited by 291
  10. 2024Long-context LLMs Struggle with Long In-context Learningcited by 285
  11. 2024MinerU: An Open-Source Solution for Precise Document Content Extractioncited by 255
  12. 2024Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimizationcited by 238
38 more
  1. 2025Inference-Time Scaling for Generalist Reward Modelingcited by 233
  2. 2025InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modelingcited by 203
  3. 2024InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Outputcited by 195
  4. 2024Building and better understanding vision-language models: insights and future directionscited by 169
  5. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
  6. 2026Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolationcited by 157
  7. 2024InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HDcited by 156
  8. 2025RM-R1: Reward Modeling as Reasoningcited by 149
  9. 2024Benchmarking Complex Instruction-Following with Multiple Constraints Compositioncited by 147
  10. 2024VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Taskscited by 136
  11. 2025VisualPRM: An Effective Process Reward Model for Multimodal Reasoningcited by 134
  12. 2024Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Inputcited by 132
  13. 2024Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiTcited by 130
  14. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 129
  15. 2024OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understandingcited by 126
  16. 2025Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reactioncited by 122
  17. 2025GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Datacited by 120
  18. 2024Make Your LLM Fully Utilize the Contextcited by 118
  19. 2024Large Language Model Unlearning via Embedding-Corrupted Promptscited by 112
  20. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  21. 2024On-Device Language Models: A Comprehensive Reviewcited by 101
  22. 2024Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performancecited by 94
  23. 2025Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMscited by 92
  24. 2024MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMscited by 89
  25. 2024How to Evaluate Reward Models for RLHFcited by 84
  26. 2025UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learningcited by 83
  27. 2024Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-trainingcited by 82
  28. 2024AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modelingcited by 76
  29. 2024Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMscited by 73
  30. 2025InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Modelcited by 73
  31. 2024LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Modelscited by 70
  32. 2024OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AIcited by 70
  33. 2024TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Abilitycited by 69
  34. 2025Transformers without Normalizationcited by 69
  35. 2024E.T. Bench: Towards Open-Ended Event-Level Video-Language Understandingcited by 68
  36. 2024SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Wordscited by 67
  37. 2024Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Comparecited by 66
  38. 2025A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluationscited by 66

50 most cited of 391 All 391 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?
  2. 2025Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models
  3. 2023Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models
  4. 2023Understanding the Effects of RLHF on LLM Generalisation and Diversity
  5. 2025MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm
  6. 2025Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them
  7. 2026In-Context Reinforcement Learning for Tool Use in Large Language Models
  8. 2023An Empirical Study of Instruction-tuning Large Language Models in Chinese