LLM Post-Training

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

29 papers in the last four weeks, up 81% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 175

All topics

Repeated post-training is not Self-improving: Diagnosing Scientific Amnesia in Continual DPO Pipelines
Jun 17, 2026Jianzhe Lin, Fei Wang, Xiaolin Li +2Continual Learning for LLMs Direct Preference Optimization
MetaAI
REVES: REvision and VErification--Augmented Training for Test-Time Scaling
Jun 17, 2026Yuanxin Liu, Ruida Zhou, Xinyan Zhao +6LLM Self-Correction LLM Answer Verification
Northwestern University · Amazon AGI · Qualcomm AI Research +1
When the Next Step Is Not One Step: Distribution-Aware Execution Modeling for Concurrent Go Programs
Jun 16, 2026Kaviru HapuarachchiLLM Post-Training
University of Colombo School of Computing, 35 Reid Avenue, Colombo 07, Sri Lanka
OdysSim: Building Foundation Models for Human Behavior Simulation
Jun 12, 2026Xuhui Zhou, Weiwei Sun, Weihua Du +6Human Behavior Simulation AI Agent Benchmarks
Carnegie Mellon University, Language Technologies Institute
Can Post-Training Turn LLMs into Good Medical Coders? An Empirical Study of Generative ICD Coding
Jun 11, 2026Ziqing Wang, Weihao Li, Shijie Chen +2Supervised Fine-Tuning Automated Medical Coding
Northwestern University
Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study
Jun 11, 2026Dezhi Yu, Yvonne Qiu, ShuoJia FuLLM Alignment Direct Preference Optimization
Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
Jun 10, 2026Leon Bergen, Usha Bhalla, Sidharth Baskaran +14Reward Shaping LLM Interpretability
Core contributors
Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation
Jun 9, 2026Soham Bhattacharjee, Karun Sharma, Vinay Kumar Sankarapu +1Adaptive Sampling LLM Post-Training
Lexsi Labs
Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation
Jun 9, 2026Yupu Hao, Zhuoran Jin, Huanxuan Liao +2Knowledge Augmentation for Language Models Inference-Time Scaling
1The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
Training LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference Optimization
Jun 9, 2026Lena S. Bolliger, Lena A. JägerDirect Preference Optimization LLM Safety Alignment
Department of Computational Linguistics, University of Zurich, Switzerland
A-Evolve-Training: Autonomous Post-Training of a 30B Model
Jun 9, 2026Zhan Shi, Bing He, Yisi Sang +2LLM Post-Training Language Model Self-Improvement
Amazon
Trajectory-Refined Distillation
Jun 7, 2026Li Jiang, Haoran Xu, Yichuan Ding +1On-Policy Distillation LLM Post-Training
McGill University · Mila Quebec AI Institute · UT Austin
TALAN: Task-Aligned Latent Adaptation Networks for Targeted Post-Training of Large Language Models
Jun 5, 2026Chengkai Zhang, Ziteng Liu, Junpu Wang +4Supervised Fine-Tuning Adapter Tuning
Meta AI
EDIT: Evidence-Diagnosed Intervention Training for Rule-Faithful LLM Grading
Jun 4, 2026Zhihao Wu, Linhai Zhang, Taiyi Wang +4LLM-as-a-Judge Rubric-Based Evaluation
1King’s College London · University of Cambridge · 3AQA +1
Sequential Data Poisoning in LLM Post-Training
Jun 3, 2026Jack Sanderson, Yihan Wang, Xiaoqian Lu +2LLM Security LLM Post-Training
University of Chicago · Vector Institute · University of Waterloo +1
MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU
Jun 3, 2026Kun Cheng, Songshuo Lu, Sicong Liao +7RL for Code Generation GPU Kernel Optimization
Moore Threads AI
POLARIS: Guiding Small Models to Write Long Stories
Jun 2, 2026Rishanth Rajendhran, Jenna Russell, Mohit Iyyer +1Length Generalization LLM Post-Training
University of Maryland · Google DeepMind
Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM-Enhanced Recommendation
Jun 2, 2026Yuecheng Li, Zeyu Song, Jing Yao +3RL for Language Models Large Language Model-Based Recommendation
Kuaishou Technology Beijing, China · Unaffiliated Beijing, China
Physics-Guided Policy Optimization with Self-Distillation
Jun 2, 2026Ke Wang, Yuning Wu, Haoran Liu +3On-Policy Self-Distillation Policy Optimization
Amazon, Arlington, USA · Amazon, New York, USA · Amazon, San Jose, USA +1
Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression
Jun 2, 2026Artur Zagitov, Alexander Miasnikov, Maxim Krutikov +5LLM Compression Tensor Decomposition
BRAIn Lab, Moscow, Russia
A Primer in Post-Training Reasoning Data: What We Know About How It Works
Jun 1, 2026Yaoming Li, Guangxiang Zhao, Qilong Shi +3RL Post-Training LLM Post-Training
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · Qiyuan Tech · Tsinghua University
ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment
May 31, 2026Zhengyang Zhao, Shengjie Ye, Lu Ma +3LLM Alignment LLM Agent Skill Learning
Peking University · Sichuan University, Chengdu
Trust Region On-Policy Distillation
May 31, 2026Xingrun Xing, Haoqing Wang, Boyan Gao +2Language Model Distillation Trust-Region Optimization
Samsung Research, Beijing, China · University of Oxford · Peking University
Enhancing LLM Metacognition via Cognitive Pairwise Training
May 30, 2026Weitao Li, Hao Zhou, Xuanyu Lei +11Pairwise Preference Learning RL for Language Model Reasoning
Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China · WeChat AI, Tencent Inc., China
Representation Collapse in Sequential Post-Training of Large Language Models
May 28, 2026Yichen Liu, Mingyu Chen, Hao Wang +7Continual Learning for LLMs Representation Collapse
Hangzhou Dianzi University · Zhejiang Gongshang University · Ningbo University +1
LLUMI: Improving LLM Writing Assistance for Mental Health Support with Online Community Feedback
May 28, 2026Jiwon Kim, Maya Ajit, Sherry Gong +4Emotional Support Conversation Privacy-Preserving Language Models
University of Illinois Urbana-Champaign · Indiana University Indianapolis
Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMs
May 28, 2026Vinay Samuel, Yapei Chang, Mohit IyyerLLM Alignment Direct Preference Optimization
University of Maryland, College Park
Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting
May 28, 2026Haoxin Liu, Yichen Zhou, Rajat Sen +2Multivariate Time Series Forecasting LLM Post-Training
Georgia Institute of Technology · Google Research
Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces
May 28, 2026Chen He, Yuhao Wu, Lei Wang +2Fine-Tuning LLM Fine-Tuning
University of Electronic Science and Technology of China · Singapore University of Technology and Design · Singapore Management University
RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains
May 27, 2026Haoxiang Jiang, Zihan Dong, Tianci Liu +5Reward Modeling RL for Language Models
University at Albany · 2Rutgers University · 3Purdue University +3

Jun 17, 2026, cs.AIJ/K move · Enter open · S save

Repeated post-training is not Self-improving: Diagnosing Scientific Amnesia in Continual DPO Pipelines

Jianzhe Lin, Fei Wang, Xiaolin Li, Rajeshkumar Golani+1

MetaAI

Continual Learning for LLMs Direct Preference Optimization LLM Post-Training Generative AI Evaluation

Open paper AskPDF arXiv

Industrial LLM teams often ship behavior updates by repeatedly DPO-training a base model on sequences of related preference-data campaigns. The dominant failure mode in this regime is not always classical catastrophic forgetting: a pipeline may preserve previously learned behaviors while still failing to accumulate reusable methodological knowledge about how to train the next campaign. We call this failure mode scientific amnesia. This paper turns that practitioner intuition into a measurable industrial problem. We contribute: (i) a diagnostic suite for amnesia, (ii) a Program-based pipeline that chains FSDP-sharded DPO checkpoints across Qwen2.5-7B-Instruct runs, (iii) a 30-campaign HumanEval subdomain benchmark, and (iv) a comparative diagnostic study of five strategy proposers: random memory, rule-based scheduling, retrieval-only memory, warm-start Bayesian optimization, and MSCL, a meta-scientific memory and reasoner candidate. Across a single-seed 5-condition * 3-step real-LM chain, 4 of 5 candidates degrade in step-level peak pass@1, including MSCL; only the deliberately conservative rule-based schedule improves. Follow-up pilots qualify rather than overturn this finding: in a heterogeneous chain, MSCL is the only completed candidate that improves, whereas in a small multi-seed homogeneous sweep, retrieval-only has the best mean Delta and no pairwise candidate gap is statistically distinguishable. The contribution is therefore diagnostic, not a claim that MSCL solves the problem: scientific amnesia is observable in a production-like continual-DPO pipeline, and conclusions about interventions depend sharply on chain regime, evaluator design, and seed coverage.

Momentum

Related topics

Latest papers 175