mlsanityData to 14 Oct 2026

AlignBench: Benchmarking Chinese Alignment of Large Language Models

arXiv 2311.18743 ↗First posted 30 Nov 2023cs.CL cs.AI cs.LGcited by 68

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

Abstract (arXiv)

Alignment has become a critical step for instruction-tuned Large Language Models (LLMs) to become helpful assistants. However, the effective evaluation of alignment for emerging Chinese LLMs is still largely unexplored. To fill in this gap, we introduce AlignBench, a comprehensive multi-dimensional benchmark for evaluating LLMs' alignment in Chinese. We design a human-in-the-loop data curation pipeline, containing eight main categories, 683 real-scenario rooted queries and corresponding human verified references. To ensure the correctness of references, each knowledge-intensive query is accompanied with evidences collected from reliable web sources (including URLs and quotations) by our annotators. For automatic evaluation, our benchmark employs a rule-calibrated multi-dimensional LLM-as-Judge~citezheng2023judging approach with Chain-of-Thought to generate explanations and final ratings, ensuring high reliability and interpretability. All evaluation code, data, and LLM generations are available at urlhttps://github.com/THUDM/AlignBench. Since its release, AlignBench has been adopted by top (Chinese) LLMs for evaluating their alignment capabilities in Chinese, including ChatGLM, Qwen, DeepSeek, Yi, Baichuan, and Abab.

Key facts. Cited by 68 papers in the map (data through 14 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 35 of its 52 references that are in the map. First posted on arXiv 30 Nov 2023.

Builds on

35 of 52 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Black-Box Prompt Optimization: Aligning Large Language Models without Model Training7 Nov
  2. 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision4 May
  3. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructions20 Dec
  4. 2022Training language models to follow instructions with human feedback4 Mar

Other references · 31

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  8. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  9. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  10. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  11. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  12. 2020Learning to summarize from human feedbackcited by 2,588
19 more
  1. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  2. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  3. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  4. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,729
  5. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  6. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,125
  7. 2023Large Language Models are not Fair Evaluatorscited by 1,085
  8. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,031
  9. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 716
  10. 2023C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Modelscited by 708
  11. 2020Self-supervised Learning: Generative or Contrastivecited by 694
  12. 2023Baichuan 2: Open Large-scale Language Modelscited by 670
  13. 2023Prometheus: Inducing Fine-grained Evaluation Capability in Language Modelscited by 575
  14. 2022Improving alignment of dialogue agents via targeted human judgementscited by 531
  15. 2023Is ChatGPT a Good NLG Evaluator? A Preliminary Studycited by 422
  16. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  17. 2023PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimizationcited by 316
  18. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 297
  19. 2023SuperCLUE: A Comprehensive Chinese Large Language Model Benchmarkcited by 50

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 35; 2025: 24; 2026: 8.

68 papers.

Sort:

By area:

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2024Qwen2 Technical Reportcited by 2,120
  3. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,135
  4. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 642
  5. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 477
  6. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 465
  7. 2024Justice or Prejudice? Quantifying Biases in LLM-as-a-Judgecited by 368
  8. 2024DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligencecited by 331
  9. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 288
  10. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 285
  11. 2024PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preferencecited by 261
  12. 2024SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusalcited by 240
38 more
  1. 2024Benchmarking Complex Instruction-Following with Multiple Constraints Compositioncited by 152
  2. 2025Preference Leakage: A Contamination Problem in LLM-as-a-judgecited by 125
  3. 2025MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttrainingcited by 121
  4. 2024Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Followingcited by 102
  5. 2024Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencentcited by 90
  6. 2024MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Seriescited by 67
  7. 2025Baichuan-M2: Scaling Medical Capability with Large Verifier Systemcited by 59
  8. 2023MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluationcited by 57
  9. 2024ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipelinecited by 47
  10. 2024CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolutioncited by 42
  11. 2024LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Modelcited by 34
  12. 2024RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarioscited by 27
  13. 2024Language Models can Self-Lengthen to Generate Long Textscited by 24
  14. 2024DataGen: Unified Synthetic Dataset Generation via Large Language Modelscited by 23
  15. 2024Does RLHF Scale? Exploring the Impacts From Data, Model, and Methodcited by 23
  16. 2024SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Modelscited by 23
  17. 2024I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBenchcited by 21
  18. 2024AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?cited by 21
  19. 2024HonestLLM: Toward an Honest and Helpful Large Language Modelcited by 18
  20. 2025Incentivizing Reasoning for Advanced Instruction-Following of Large Language Modelscited by 17
  21. 2025Pre-Trained Policy Discriminators are General Reward Modelscited by 15
  22. 2025Aligning Multimodal LLM with Human Preference: A Surveycited by 13
  23. 2024Yi-Lightning Technical Reportcited by 12
  24. 2025From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuningcited by 12
  25. 2025CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewardscited by 12
  26. 202452B to 1T: Lessons Learned via Tele-FLM Seriescited by 11
  27. 2025EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solvingcited by 10
  28. 2025Technical Report of TeleChat2, TeleChat2.5 and T1cited by 10
  29. 2026PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarioscited by 10
  30. 2025Megrez-Omni Technical Reportcited by 7
  31. 2025Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learningcited by 7
  32. 2024On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboardscited by 6
  33. 2025FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusioncited by 6
  34. 2025Beyond Correctness: Evaluating Subjective Writing Preferences Across Culturescited by 6
  35. 2026WavBench: Benchmarking Reasoning, Colloquialism, and Paralinguistics for End-to-End Spoken Dialogue Modelscited by 6
  36. 2024CourseGPT-zh: an Educational Large Language Model Based on Knowledge Distillation Incorporating Prompt Optimizationcited by 5
  37. 2024Extensive Self-Contrast Enables Feedback-Free Language Model Alignmentcited by 4
  38. 2024Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularitycited by 4

50 most cited of 68 All 68 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety
  2. 2025A Comprehensive Evaluation framework of Alignment Techniques for LLMs
  3. 2024Efficient Alignment of Large Language Models via Data Sampling
  4. 2024LongAlign: A Recipe for Long Context Alignment of Large Language Models
  5. 2026Are Aligned Large Language Models Still Misaligned?
  6. 2024AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models
  7. 2023ArcMMLU: A Library and Information Science Benchmark for Large Language Models
  8. 2025Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety