Cover Image

Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Damani, Mehul, Puri, Isha, Slocum, Stewart, Shenfeld, Idan, Choshen, Leshem, Kim, Yoon, Andreas, Jacob
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models
by: Puri, Isha, et al.
Published: (2026)

Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
by: Damani, Mehul, et al.
Published: (2024)

Vector Policy Optimization: Training for Diversity Improves Test-Time Search
by: Bahlous-Boldi, Ryan, et al.
Published: (2026)

A Hitchhiker's Guide to Scaling Law Estimation
by: Choshen, Leshem, et al.
Published: (2024)

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users
by: Hilel, Almog, et al.
Published: (2025)

The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
by: Akyürek, Ekin, et al.
Published: (2024)

Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMs
by: Ifergan, Maxim, et al.
Published: (2024)

Do LLMs Benefit From Their Own Words?
by: Huang, Jenny Y., et al.
Published: (2026)

Value Augmented Sampling for Language Model Alignment and Personalization
by: Han, Seungwook, et al.
Published: (2024)

Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion
by: Zaman, Kerem, et al.
Published: (2023)

CRISP: Complex Reasoning with Interpretable Step-based Plans
by: Vetzler, Matan, et al.
Published: (2025)

ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization
by: Yadav, Prateek, et al.
Published: (2023)

Self-Distillation Enables Continual Learning
by: Shenfeld, Idan, et al.
Published: (2026)

ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models
by: Ashury-Tahan, Shir, et al.
Published: (2026)

What We Talk About When We Talk About LMs: Implicit Paradigm Shifts and the Ship of Language Models
by: Zhu, Shengqi, et al.
Published: (2024)

Latency and Token-Aware Test-Time Compute
by: Huang, Jenny Y., et al.
Published: (2025)

Beyond the Binary: Capturing Diverse Preferences With Reward Regularization
by: Padmakumar, Vishakh, et al.
Published: (2024)

Aligning Language Models from User Interactions
by: Buening, Thomas Kleine, et al.
Published: (2026)

Can Gradient Descent Simulate Prompting?
by: Zhang, Eric, et al.
Published: (2025)

Great Memory, Shallow Reasoning: Limits of $k$NN-LMs
by: Geng, Shangyi, et al.
Published: (2024)

Robustness as an Emergent Property of Task Performance
by: Ashury-Tahan, Shir, et al.
Published: (2026)

When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs
by: Jeong, Soyeong, et al.
Published: (2025)

Beyond Learning: A Training-Free Alternative to Model Adaptation
by: Yoon, Namkyung, et al.
Published: (2026)

tinyBenchmarks: evaluating LLMs with fewer examples
by: Polo, Felipe Maia, et al.
Published: (2024)

Thinking About Thinking: SAGE-nano's Inverse Reasoning for Self-Aware Language Models
by: Jha, Basab, et al.
Published: (2025)

Resolving Interference (RI): Disentangling Models for Improved Model Merging
by: Ramesh, Pratik, et al.
Published: (2026)

Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations
by: Bochkov, A.
Published: (2025)

PACR: Progressively Ascending Confidence Reward for LLM Reasoning
by: Yoon, Eunseop, et al.
Published: (2025)

TextArena
by: Guertler, Leon, et al.
Published: (2025)

Language Statistics and False Belief Reasoning: Evidence from 41 Open-Weight LMs
by: Trott, Sean, et al.
Published: (2026)

Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
by: Prashanth, USVSN Sai, et al.
Published: (2024)

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

Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards
by: Han, Tianyang, et al.
Published: (2026)

Beyond Outcome Verification: Verifiable Process Reward Models for Structured Reasoning
by: Pronesti, Massimiliano, et al.
Published: (2026)

Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability
by: Akyürek, Afra Feyza, et al.
Published: (2024)

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
by: Wu, Zhaofeng, et al.
Published: (2023)

Bias Dynamics in BabyLMs: Towards a Compute-Efficient Sandbox for Democratising Pre-Training Debiasing
by: Trhlik, Filip, et al.
Published: (2026)

Genie: Achieving Human Parity in Content-Grounded Datasets Generation
by: Yehudai, Asaf, et al.
Published: (2024)

Reasoning Models Will Sometimes Lie About Their Reasoning
by: Walden, William, et al.
Published: (2026)

MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formula
by: Hyeon, Sieun, et al.
Published: (2024)