Buchumschlag

Training Emergent Joint Associations: A Reinforcement Learning Approach to Creative Thinking in Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Singh, Mukul, Singha, Ananya, Parab, Aishni, Mehrotra, Pronita, Gulwani, Sumit
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Enhancing Creativity in Large Language Models through Associative Thinking Strategies
von: Mehrotra, Pronita, et al.
Veröffentlicht: (2024)

Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction
von: Parab, Aishni, et al.
Veröffentlicht: (2025)

Collaboration and Conflict between Humans and Language Models through the Lens of Game Theory
von: Singh, Mukul, et al.
Veröffentlicht: (2025)

Exploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creation with Generative Models
von: Wen, Chao, et al.
Veröffentlicht: (2025)

Scaling Competence, Shrinking Reasoning: Cognitive Signatures in Language Model Learning
von: Singh, Mukul, et al.
Veröffentlicht: (2025)

Do Code Models Suffer from the Dunning-Kruger Effect?
von: Singh, Mukul, et al.
Veröffentlicht: (2025)

MetaReflection: Learning Instructions for Language Agents using Past Reflections
von: Gupta, Priyanshu, et al.
Veröffentlicht: (2024)

Diffusion is a code repair operator and generator
von: Singh, Mukul, et al.
Veröffentlicht: (2025)

Semantically Aligned Question and Code Generation for Automated Insight Generation
von: Singha, Ananya, et al.
Veröffentlicht: (2024)

Tabularis Formatus: Predictive Formatting for Tables
von: Singh, Mukul, et al.
Veröffentlicht: (2025)

TEN: Table Explicitization, Neurosymbolically
von: Mehrotra, Nikita, et al.
Veröffentlicht: (2025)

Counterfactual Self-Questioning for Stable Policy Optimization in Language Models
von: Parab, Mandar
Veröffentlicht: (2025)

An Empirical Study of Validating Synthetic Data for Formula Generation
von: Singh, Usneek, et al.
Veröffentlicht: (2024)

An Empirical Investigation of Robustness in Large Language Models under Tabular Distortions
von: Dutta, Avik, et al.
Veröffentlicht: (2026)

Automated Analysis of Learning Outcomes and Exam Questions Based on Bloom's Taxonomy
von: Kumar, Ramya, et al.
Veröffentlicht: (2025)

Thinking About Thinking: Evaluating Reasoning in Post-Trained Language Models
von: Singla, Pratham, et al.
Veröffentlicht: (2025)

Improving Language Agents through BREW
von: Kirtania, Shashank, et al.
Veröffentlicht: (2025)

Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training
von: Park, Yein, et al.
Veröffentlicht: (2025)

IndiMathBench: Autoformalizing Mathematical Reasoning Problems with a Human Touch
von: Biyani, Param, et al.
Veröffentlicht: (2025)

ConDABench: Interactive Evaluation of Language Models for Data Analysis
von: Dutta, Avik, et al.
Veröffentlicht: (2025)

Divergent-Convergent Thinking in Large Language Models for Creative Problem Generation
von: Nguyen, Manh Hung, et al.
Veröffentlicht: (2025)

Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation
von: Phung, Tung, et al.
Veröffentlicht: (2023)

Emergent Ordinal Geometry in Transformers Trained on Local Comparisons
von: Singh, Nishit
Veröffentlicht: (2026)

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
von: Gan, Siyuan, et al.
Veröffentlicht: (2026)

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
von: Liao, Yi, et al.
Veröffentlicht: (2025)

Large Language Models Align with the Human Brain during Creative Thinking
von: Ismayilzada, Mete, et al.
Veröffentlicht: (2026)

In-Training Defenses against Emergent Misalignment in Language Models
von: Kaczér, David, et al.
Veröffentlicht: (2025)

ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement
von: Jiao, Difan, et al.
Veröffentlicht: (2026)

Interpreting Emergent Planning in Model-Free Reinforcement Learning
von: Bush, Thomas, et al.
Veröffentlicht: (2025)

Think before you speak: Training Language Models With Pause Tokens
von: Goyal, Sachin, et al.
Veröffentlicht: (2023)

When Can Model-Free Reinforcement Learning be Enough for Thinking?
von: Hanna, Josiah P., et al.
Veröffentlicht: (2025)

Balanced Thinking: Improving Chain of Thought Training in Vision Language Models
von: Perek, Shaked, et al.
Veröffentlicht: (2026)

Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
von: Wang, Jiaqi, et al.
Veröffentlicht: (2025)

DeepMath-Creative: A Benchmark for Evaluating Mathematical Creativity of Large Language Models
von: Chen, Xiaoyang, et al.
Veröffentlicht: (2025)

Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models
von: RRV, Aswin, et al.
Veröffentlicht: (2026)

Large Language Model as a Policy Teacher for Training Reinforcement Learning Agents
von: Zhou, Zihao, et al.
Veröffentlicht: (2023)

Automated Creativity Evaluation for Large Language Models: A Reference-Based Approach
von: Li, Ruizhe, et al.
Veröffentlicht: (2025)

Discovering Reinforcement Learning Interfaces with Large Language Models
von: Jaswal, Akshat Singh, et al.
Veröffentlicht: (2026)

Learning Under Laws: A Constraint-Projected Neural PDE Solver that Eliminates Hallucinations
von: Singha, Mainak
Veröffentlicht: (2025)

RLInspect: An Interactive Visual Approach to Assess Reinforcement Learning Algorithm
von: Kalra, Geetansh, et al.
Veröffentlicht: (2024)