Language Model Post-Training

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

208 papers26 papers in the last four weeks, down 35% on the four weeks before. 0.2% of all new papers.

  1. TrainExplorer: Autonomous LLM Post-Training via Plan-and-Decouple Exploration

    Nov 16, 2026Xuannan Liu, Tian Lan, Zekun Li +9LLM Post-TrainingLanguage Model Post-Training

  2. Augmenting Pretrained Language Models with N-gram Embeddings through Incremental Training

    Nov 16, 2026Shaohua Hu, Xusheng Gu, Haofei Yang +4Knowledge Augmentation for Language ModelsLanguage Model Post-Training

  3. VWEN: A Curated Small Language Model for Vietnamese Paraphrasing

    Nov 11, 2026Sang Quang NguyenLanguage Model Post-TrainingText Generation

  4. Trait Hitchhiking in LLM Post-Training

    Nov 10, 2026Adil Soubki, Elizabeth S. Z. Tan, Miles CranmerLanguage Model Post-TrainingRL Post-Training

  5. Learning Dynamics of On-Policy Distillation

    Nov 5, 2026Guan Zhe Hong, Sumeet Ramesh Motwani, Liang Chen +5On-Policy DistillationLanguage Model Distillation

  6. Reinforcing What the Student Has Learned: Teacher-Guided On-Policy Distillation

    Nov 5, 2026Bozhen Fang, Linhao Zhong, Xuehao Wang +3Language Model DistillationOn-Policy Distillation

  7. Unifying and Beyond the Theory of Pervasive Capability Degradation in LLM Post-training SFT from Feature Interference

    Nov 3, 2026Hang Chen, Jiaying Zhu, Wenya WangLanguage Model Post-TrainingFine-Tuning Language Models

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

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

  9. 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

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

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

  11. 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

  12. Training Small Language Models for Transferable Tool Selection

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

  13. Unintended Side Effects of Value Training in LLMs

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

  14. 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

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

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

  16. 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

  17. Analyzing Occupational Gender Bias across the LLM Training Lifecycle

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

  18. 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