Cover Image

Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sundaram, Shobhita, Quan, John, Kwiatkowski, Ariel, Ahuja, Kartik, Ollivier, Yann, Kempe, Julia
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Soft Tokens, Hard Truths
by: Butt, Natasha, et al.
Published: (2025)

Likelihood-Based Reward Designs for General LLM Reasoning
by: Kwiatkowski, Ariel, et al.
Published: (2026)

DRoP: Distributionally Robust Data Pruning
by: Vysogorets, Artem, et al.
Published: (2024)

On Provable Length and Compositional Generalization
by: Ahuja, Kartik, et al.
Published: (2024)

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
by: Zelikman, Eric, et al.
Published: (2024)

Outcome-based Exploration for LLM Reasoning
by: Song, Yuda, et al.
Published: (2025)

Teaching Transformers Causal Reasoning through Axiomatic Training
by: Vashishtha, Aniket, et al.
Published: (2024)

ORION: Teaching Language Models to Reason Efficiently in the Language of Thought
by: Tanmay, Kumar, et al.
Published: (2025)

NExT: Teaching Large Language Models to Reason about Code Execution
by: Ni, Ansong, et al.
Published: (2024)

PILAF: Optimal Human Preference Sampling for Reward Modeling
by: Feng, Yunzhen, et al.
Published: (2025)

Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code
by: Bao, Keqin, et al.
Published: (2025)

From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers
by: Su, Jingtong, et al.
Published: (2025)

Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
by: Su, Jingtong, et al.
Published: (2024)

Personalized Representation from Personalized Generation
by: Sundaram, Shobhita, et al.
Published: (2024)

Learning to Reason at the Frontier of Learnability
by: Foster, Thomas, et al.
Published: (2025)

Teaching Models to Understand (but not Generate) High-risk Data
by: Wang, Ryan, et al.
Published: (2025)

Reasoning Boosts Opinion Alignment in LLMs
by: Berdoz, Frédéric, et al.
Published: (2026)

Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification
by: Donhauser, Konstantin, et al.
Published: (2025)

Uncertainty Distillation: Teaching Language Models to Express Semantic Confidence
by: Hager, Sophia, et al.
Published: (2025)

ReasonCACHE: Teaching LLMs To Reason Without Weight Updates
by: Gupta, Sharut, et al.
Published: (2026)

AgreeMate: Teaching LLMs to Haggle
by: Chatterjee, Ainesh, et al.
Published: (2024)

When Actions Teach You to Think: Reasoning-Action Synergy via Reinforcement Learning in Conversational Agents
by: Rawat, Mrinal, et al.
Published: (2025)

A Tale of Tails: Model Collapse as a Change of Scaling Laws
by: Dohmatob, Elvis, et al.
Published: (2024)

Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models
by: Gupta, Sharut, et al.
Published: (2025)

Efficient Reasoning on the Edge
by: Bondarenko, Yelysei, et al.
Published: (2026)

Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
by: McLeish, Sean, et al.
Published: (2025)

Learnable Permutation for Structured Sparsity on Transformer Models
by: Li, Zekai, et al.
Published: (2026)

Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language
by: Kumar, Vinayshekhar Bannihatti, et al.
Published: (2026)

GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler
by: Wang, Minghan, et al.
Published: (2026)

Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards
by: Arnal, Charles, et al.
Published: (2025)

When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing
by: Dadfar, Zachary Pedram
Published: (2026)

Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves
by: Deng, Yihe, et al.
Published: (2023)

Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationales
by: Qian, Zhen, et al.
Published: (2025)

Reference-based Metrics Disprove Themselves in Question Generation
by: Nguyen, Bang, et al.
Published: (2024)

Teaching Language Models to Critique via Reinforcement Learning
by: Xie, Zhihui, et al.
Published: (2025)

Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability
by: Xu, Chenhui, et al.
Published: (2025)

Teaching LLMs How to Learn with Contextual Fine-Tuning
by: Choi, Younwoo, et al.
Published: (2025)

Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation
by: Bhardwaj, Dhrupad, et al.
Published: (2025)

CEV-LM: Controlled Edit Vector Language Model for Shaping Natural Language Generations
by: Moorjani, Samraj, et al.
Published: (2024)

On the Learnability of Watermarks for Language Models
by: Gu, Chenchen, et al.
Published: (2023)