Image de couverture de livre

DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Yicheng, Ma, Zerun, Xie, Xinchen, Li, Yining, Chen, Kai
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space
par: Chen, Yicheng, et autres
Publié: (2025)

TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration
par: Ma, Zerun, et autres
Publié: (2026)

Losses that Cook: Topological Optimal Transport for Structured Recipe Generation
par: Ottoborgo, Mattia, et autres
Publié: (2026)

GTA: A Benchmark for General Tool Agents
par: Wang, Jize, et autres
Publié: (2024)

Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination
par: Mizrahi, Moran, et autres
Publié: (2025)

Rethinking Data Synthesis: A Teacher Model Training Recipe with Interpretation
par: Chen, Yifang, et autres
Publié: (2024)

Domain-Specific Data Generation Framework for RAG Adaptation
par: Tian, Chris Xing, et autres
Publié: (2025)

Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling
par: Sun, Shengyin, et autres
Publié: (2025)

CGU-ILALab at FoodBench-QA 2026: Comparing Traditional and LLM-based Approaches for Recipe Nutrient Estimation
par: Chen, Wei-Chun, et autres
Publié: (2026)

Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents
par: Zhang, Xing, et autres
Publié: (2026)

CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents
par: Sutawika, Lintang, et autres
Publié: (2026)

Learning from Response not Preference: A Stackelberg Approach for LLM Detoxification using Non-parallel Data
par: Xie, Xinhong, et autres
Publié: (2024)

Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement
par: Cao, Maosong, et autres
Publié: (2025)

R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
par: Li, Yuan, et autres
Publié: (2025)

Boosting LLM via Learning from Data Iteratively and Selectively
par: Jia, Qi, et autres
Publié: (2024)

FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination
par: Zhou, Pengfei, et autres
Publié: (2024)

Ranking Unraveled: Recipes for LLM Rankings in Head-to-Head AI Combat
par: Daynauth, Roland, et autres
Publié: (2024)

Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
par: Xie, Tian, et autres
Publié: (2025)

Enhancing Action and Ingredient Modeling for Semantically Grounded Recipe Generation
par: Liu, Guoshan, et autres
Publié: (2026)

Reinforcement Learning on Pre-Training Data
par: Li, Siheng, et autres
Publié: (2025)

Improving Data Efficiency via Curating LLM-Driven Rating Systems
par: Pang, Jinlong, et autres
Publié: (2024)

Data Compressibility Quantifies LLM Memorization
par: Huang, Yizhan, et autres
Publié: (2025)

GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning
par: Yang, Ningyuan, et autres
Publié: (2026)

MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
par: Zhao, Changsheng, et autres
Publié: (2025)

LESA: Learnable LLM Layer Scaling-Up
par: Yang, Yifei, et autres
Publié: (2025)

Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
par: Chen, Sirui, et autres
Publié: (2026)

Teaching Language Models to Critique via Reinforcement Learning
par: Xie, Zhihui, et autres
Publié: (2025)

SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data
par: Fang, Wenkai, et autres
Publié: (2025)

CAST: Achieving Stable LLM-based Text Analysis for Data Analytics
par: Xie, Jinxiang, et autres
Publié: (2026)

Safer-Instruct: Aligning Language Models with Automated Preference Data
par: Shi, Taiwei, et autres
Publié: (2023)

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
par: Chen, Mingyang, et autres
Publié: (2025)

ProMind-LLM: Proactive Mental Health Care via Causal Reasoning with Sensor Data
par: Zheng, Xinzhe, et autres
Publié: (2025)

SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training
par: He, Nan, et autres
Publié: (2024)

Domain Adaptation of LLMs for Process Data
par: Oyamada, Rafael Seidi, et autres
Publié: (2025)

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
par: Sun, Yifan, et autres
Publié: (2025)

AddrLLM: Address Rewriting via Large Language Model on Nationwide Logistics Data
par: Yang, Qinchen, et autres
Publié: (2024)

Optimizing Decomposition for Optimal Claim Verification
par: Lu, Yining, et autres
Publié: (2025)

On the Step Length Confounding in LLM Reasoning Data Selection
par: Wang, Bing, et autres
Publié: (2026)

Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
par: Shen, Maohao, et autres
Publié: (2025)

Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies
par: Song, Jingze, et autres
Publié: (2026)