Copertina

Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Puri, Isha, Damani, Mehul, Shenfeld, Idan, Ghassemi, Marzyeh, Andreas, Jacob, Kim, Yoon
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
di: Damani, Mehul, et al.
Pubblicazione: (2025)

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

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

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

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

SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe
di: Xiao, Yuxin, et al.
Pubblicazione: (2024)

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

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

KScope: A Framework for Characterizing the Knowledge Status of Language Models
di: Xiao, Yuxin, et al.
Pubblicazione: (2025)

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

Train Long, Think Short: Curriculum Learning for Efficient Reasoning
di: Hammoud, Hasan Abed Al Kader, et al.
Pubblicazione: (2025)

Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
di: Chan, Yik Siu, et al.
Pubblicazione: (2025)

Curiosity-driven Red-teaming for Large Language Models
di: Hong, Zhang-Wei, et al.
Pubblicazione: (2024)

When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment
di: Xiao, Yuxin, et al.
Pubblicazione: (2025)

On the Optimal Reasoning Length for RL-Trained Language Models
di: Nohara, Daisuke, et al.
Pubblicazione: (2026)

FlowRL: Matching Reward Distributions for LLM Reasoning
di: Zhu, Xuekai, et al.
Pubblicazione: (2025)

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

Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models
di: Sun, Shaoning, et al.
Pubblicazione: (2026)

Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
di: Zhang, Shenao, et al.
Pubblicazione: (2025)

LoPT: Low-Rank Prompt Tuning for Parameter Efficient Language Models
di: Guo, Shouchang, et al.
Pubblicazione: (2024)

RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
di: Zha, Kaiwen, et al.
Pubblicazione: (2025)

MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making
di: Kim, Yubin, et al.
Pubblicazione: (2024)

ELF: Embedded Language Flows
di: Hu, Keya, et al.
Pubblicazione: (2026)

Atlas-Alignment: Making Interpretability Transferable Across Language Models
di: Puri, Bruno, et al.
Pubblicazione: (2025)

AutoTask: Task Aware Multi-Faceted Single Model for Multi-Task Ads Relevance
di: Guo, Shouchang, et al.
Pubblicazione: (2024)

MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering
di: Hao, Yuexing, et al.
Pubblicazione: (2025)

BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models
di: Srivastava, Gaurav, et al.
Pubblicazione: (2025)

Can AI Relate: Testing Large Language Model Response for Mental Health Support
di: Gabriel, Saadia, et al.
Pubblicazione: (2024)

Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?
di: Kang, Deokhyung, et al.
Pubblicazione: (2025)

Beyond Labels: Aligning Large Language Models with Human-like Reasoning
di: Kabir, Muhammad Rafsan, et al.
Pubblicazione: (2024)

Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling
di: Zhuang, Chengxu, et al.
Pubblicazione: (2024)

Training Language Models to Explain Their Own Computations
di: Li, Belinda Z., et al.
Pubblicazione: (2025)

Circuit Insights: Towards Interpretability Beyond Activations
di: Golimblevskaia, Elena, et al.
Pubblicazione: (2025)

Learning to Interpret Weight Differences in Language Models
di: Goel, Avichal, et al.
Pubblicazione: (2025)

(How) Do Language Models Track State?
di: Li, Belinda Z., et al.
Pubblicazione: (2025)

Chain of Simulation: A Dual-Mode Reasoning Framework for Large Language Models with Dynamic Problem Routing
di: Sheikhi, Saeid
Pubblicazione: (2026)

CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities
di: Mao, Yujun, et al.
Pubblicazione: (2024)

GLIDE-RL: Grounded Language Instruction through DEmonstration in RL
di: Kharyal, Chaitanya, et al.
Pubblicazione: (2024)

Evaluating the Limits of Large Language Models in Multilingual Legal Reasoning
di: Ioannou, Antreas, et al.
Pubblicazione: (2025)

Self-Training Elicits Concise Reasoning in Large Language Models
di: Munkhbat, Tergel, et al.
Pubblicazione: (2025)