Language Model Post-Training

Ask about this topic

Overview

Language model post-training studies how to turn a pretrained model into a more useful, reliable, or specialized system without training it from scratch. Common approaches include supervised fine-tuning on demonstrations, preference optimization such as DPO, reinforcement learning with human or verifiable rewards, and distillation from other models. Researchers apply these methods to tasks from mathematical reasoning and coding to translation, tool use, and domain-specific work, evaluating both task performance and qualities such as calibration, safety, and diversity. A central tension is that gains on targeted tasks can come with weaker generalization or loss of capabilities, and which methods work best often depends on the model, data, and evaluation setting.

Latest papers

CardsList

197 papers47 papers in the last four weeks, up 104% on the four weeks before. 0.3% of all new papers.

  1. From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers Believe

    Oct 28, 2026Nouar AlDahoul, Yasir ZakiSocial Bias in Language ModelsLanguage Model Bias Evaluation

    New York University Abu Dhabi

  2. LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation

    Oct 27, 2026Nesta Midavaine, Floris Fok, Paulo Mendes +4Uplift ModelingConversion Rate Prediction

    Prosus, Amsterdam, The Netherlands · iFood, São Paulo, Brazil

  3. What a Weight Update Buys: Leverage Across Training Stages

    Oct 27, 2026Shikhar ShiromaniTransformer Training DynamicsLanguage Model Post-Training

  4. From Generation to Scoring: Scaling LLM-Based Semantic Labeling at LinkedIn

    Oct 26, 2026Jian Sheng, Sriram Vasudevan, Sundara Raman Ramachandran +12Efficient Language Model InferenceText Classification

    LinkedIn.

  5. ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains?

    Oct 25, 2026Haojin Wang, Yangzhen Wu, Zeyi Chen +6LLM Agent Self-ImprovementLanguage Model Post-Training

    University of Illinois Urbana-Champaign · University of California, Berkeley · The Ohio State University +2

  6. The LALA Benchmark: Evaluating Literary and Linguistic Analysis in LLMs

    Oct 25, 2026Michael Foster, Barbara McGillivray, Gard B. Jenset +7LLM EvaluationLanguage Model Post-Training

    LALA Labs · King's College London · Ghent University +5

  7. A Comprehensive Framework for All Stages of Large-Model Training: From Data and Tokenization, through Pretraining, to Post-Training Alignment

    Oct 24, 2026Xiangjing An, Zhibin Jiao, Aiting ChenLLM TrainingLanguage Model Post-Training

    Independent Researcher Team

  8. When Does Pre-Trained Capacity Help Causal Learning? From Scalar Prediction to Counterfactual Post-Training

    Oct 23, 2026Qi Xu, Zijie Lei, Zhifei Deng +2Causal InferenceCausal Effect Estimation

    Meta Platforms, Inc., Sunnyvale, CA, USA

  9. NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding

    Oct 23, 2026Nilesh Prasad Pandey, Jangseon Park, Jason Kong +2Speculative DecodingLLM Inference Acceleration

    University of California San Diego La Jolla, CA, USA · West Virginia University Morgantown, WV, USA

  10. Training Small Language Models for Transferable Tool Selection

    Oct 22, 2026Zhaoyi Zhou, Akshayaa Magesh, Jeongyeol Kwon +4Tool Selection for Language Model AgentsSmall Language Models

    Meta · Carnegie Mellon University

  11. Unintended Side Effects of Value Training in LLMs

    Oct 21, 2026Siddhesh Pawar, Chen Cecilia Liu, Anna Korhonen +1LLM AlignmentLanguage Model Post-Training

    University of Copenhagen · University of Cambridge

  12. Every Part Has Its Role: Part-of-Speech Effects in LLM Post-Training

    Oct 21, 2026Laya Iyer, Chen ShaniLanguage Model Post-TrainingKnowledge Augmentation for Language Models

    Stanford University · Tel Aviv University

  13. Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training

    Oct 20, 2026Zhizhuo Kou, Heming Li, Jian Yang +4Dialect Bias in Language ModelsLanguage Model Post-Training

    1The Hong Kong University of Science and Technology · 2The Hong Kong University of Science and Technology (Guangzhou) · Peking University

  14. How Language Models Learn Taste: Brand Preference in LLMs

    Oct 20, 2026Tapan ParikhLanguage Model Post-TrainingPreference Modeling

    Cornell Tech

  15. Building Telecom Language Models with RSOD: Domain Data, Specialist Post-Training, Memory-Conscious Distillation, and Networking Evaluation

    Oct 20, 2026Anil Srirangapatna Nagesh, Nitin Gupta, Anuj Taneja +5Language Model Post-TrainingKnowledge Distillation

    Calix AI Labs

  16. The Development of Sycophancy in Language Models: Tracing Vulnerabilities from Pretraining to Post-Training

    Oct 19, 2026Haonan Huang, Chengkun CaiLLM SycophancyLanguage Model Post-Training

    Princeton University · University College London

  17. Correctness-Dependent Asymmetric Target Distributions for Self-Distillation Policy Optimization

    Oct 19, 2026Suwan Yoon, Seongryong Jung, Changhee LeeLanguage Model Post-TrainingOn-Policy Self-Distillation

    Korea University, Seoul, Korea · Chung-Ang University, Seoul, Korea

  18. No Matter Who You Are: Addressivity and Sycophancy in Large Language Models

    Oct 19, 2026Seungjong Sun, Hyunmin Jun, Minsik Yoon +4LLM SycophancyLanguage Model Post-Training

    Department of Human-Artificial Intelligence Interaction, Sungkyunkwan University · Department of Applied Artificial Intelligence, Sungkyunkwan University · Department of Interaction Science, Sungkyunkwan University

  19. Analyzing Occupational Gender Bias across the LLM Training Lifecycle

    Oct 16, 2026Manthan Gadhia, Alexander Hoyle, Karolina StańczakGender Bias in Language ModelsLanguage Model Post-Training

    Department of Humanities, Social, and Political Sciences, ETH Zürich · TU Wien, Complexity Science Hub · ETH AI Center, ETH Zürich

  20. Many Biases, One Circuit: Post-Training Tunes a Pretrained Cue-Routing Mechanism

    Oct 16, 2026Prakhar Gupta, Terry Jingchen Zhang, Zhijing JinCognitive Bias in Language ModelsCircuits in Language Models

    University of Michigan · Jinesis Lab, University of Toronto & Vector Institute · University of Oxford +2

  21. EliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity Search

    Oct 15, 2026Hanane Nour Moussa, Doeun Lee, Sachin KumarLanguage Model Post-TrainingRL Post-Training

    The Ohio State University

  22. Data Strategies for Large Language Models: A Unified Perspective on the Training Lifecycle

    Oct 15, 2026Yuanjian Xu, Jianing Hao, Tianze Sun +7LLM TrainingData Mixture Optimization

    The Hong Kong University of Science and Technology (Guangzhou) · Harbin Institute of Technology · OpenCSG +4

  23. Athanor: An Agent-Native System for Autonomous Post-Training Research

    Oct 15, 2026Yufa Zhou, Yichen Wang, Jiakun Fan +5LLM Post-TrainingLanguage Model Post-Training

    ByteDance · Duke University · The University of Chicago +1

  24. Beyond Correctness: Compute-Responsive Data Selection for Reasoning Model Post-Training

    Oct 14, 2026Liang He, Xiangyu Li, Yuxin Wang +4Training Data SelectionLanguage Model Post-Training

  25. RL Post-Training Diffusion Language Models Along Their Own Generation Paths

    Oct 12, 2026Vaibhav Singh, Eugene BelilovskyLanguage Model Post-TrainingRL for Diffusion Models

    Mila, Concordia University

  26. SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise

    Oct 12, 2026Xupeng Chen, Chenqian Le, Jiayi Cheng +2Language Model Post-TrainingLLM Training

    New York University · University of Southern California · Columbia University

  27. What Matters in Preference Post-Training of Continuous Autoregressive Speech Language Models

    Oct 12, 2026Yingda Shen, Yao Qian, Dekun Chen +6Speech Language ModelsLanguage Model Post-Training

    The Chinese University of Hong Kong, Shenzhen · Microsoft Research

  28. Personalized LLM Recommendation with Semantic IDs: Autoregressive Beam Search vs. Multi-Token Prediction

    Oct 11, 2026Sejoon Oh, Fernando Amat Gil, Evan Smothers +11Large Language Model-Based RecommendationSemantic ID Recommendation

    Netflix Personalization Foundations Team

  29. Select or Rewrite: Oracle-Guided Fine-Tuning for Generative ASR Post-Editing from N-Best Hypotheses

    Oct 10, 2026Shiran Liu, Gaohui Xu, Sergio Burdisso +3Language Model Post-TrainingFine-Tuning

    Idiap Research Institute, Martigny, Switzerland · KTH Royal Institute of Technology, Stockholm, Sweden · Brno University of Technology, Brno, Czech Republic

  30. From Transfer Probes to Expert Grouping: Evidence from LoRA Post-Training

    Oct 10, 2026Xueyang WuLanguage Model Post-TrainingMixture-of-Experts Models