Imagen de Portada

RATIONALYST: Mining Implicit Rationales for Process Supervision of Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jiang, Dongwei, Wang, Guoxuan, Lu, Yining, Wang, Andrew, Zhang, Jingyu, Liu, Chuyu, Van Durme, Benjamin, Khashabi, Daniel
Formato:	Preprint
Publicado:	2024
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses
por: Jiang, Dongwei, et al.
Publicado: (2024)

Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
por: Zhang, Jingyu, et al.
Publicado: (2024)

RORA: Robust Free-Text Rationale Evaluation
por: Jiang, Zhengping, et al.
Publicado: (2024)

Many-Tier Instruction Hierarchy in LLM Agents
por: Zhang, Jingyu, et al.
Publicado: (2026)

Crystal: Characterizing Relative Impact of Scholarly Publications
por: Collison, Hannah, et al.
Publicado: (2026)

"According to ...": Prompting Language Models Improves Quoting from Pre-Training Data
por: Weller, Orion, et al.
Publicado: (2023)

Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation
por: Wang, Hexuan, et al.
Publicado: (2026)

Language Models and Logic Programs for Trustworthy Tax Reasoning
por: Jurayj, William, et al.
Publicado: (2025)

Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores
por: Chari, Vivek, et al.
Publicado: (2025)

Always Tell Me The Odds: Fine-grained Conditional Probability Estimation
por: Wang, Liaoyaqi, et al.
Publicado: (2025)

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
por: Mishra, Aayush, et al.
Publicado: (2025)

Reframing Tax Law Entailment as Analogical Reasoning
por: Zou, Xinrui, et al.
Publicado: (2024)

SEQR: Secure and Efficient QR-based LoRA Routing
por: Fleshman, William, et al.
Publicado: (2025)

LoRA-Augmented Generation (LAG) for Knowledge-Intensive Language Tasks
por: Fleshman, William, et al.
Publicado: (2025)

RE-Adapt: Reverse Engineered Adaptation of Large Language Models
por: Fleshman, William, et al.
Publicado: (2024)

SpectR: Dynamically Composing LM Experts with Spectral Routing
por: Fleshman, William, et al.
Publicado: (2025)

AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies
por: Ye, Xiao, et al.
Publicado: (2024)

MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction
por: Jiang, Han, et al.
Publicado: (2024)

LM Agents for Coordinating Multi-User Information Gathering
por: Jhamtani, Harsh, et al.
Publicado: (2025)

KV-Distill: Nearly Lossless Learnable Context Compression for LLMs
por: Chari, Vivek, et al.
Publicado: (2025)

Tur[k]ingBench: A Challenge Benchmark for Web Agents
por: Xu, Kevin, et al.
Publicado: (2024)

From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLMs
por: Wang, Shaojie, et al.
Publicado: (2026)

Bonsai: Interpretable Tree-Adaptive Grounded Reasoning
por: Sanders, Kate, et al.
Publicado: (2025)

GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution
por: Lu, Yining, et al.
Publicado: (2023)

RE-AdaptIR: Improving Information Retrieval through Reverse Engineered Adaptation
por: Fleshman, William, et al.
Publicado: (2024)

Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data
por: Zhang, Jingyu, et al.
Publicado: (2024)

Certified Mitigation of Worst-Case LLM Copyright Infringement
por: Zhang, Jingyu, et al.
Publicado: (2025)

Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic
por: Weir, Nathaniel, et al.
Publicado: (2024)

Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models
por: Jiang, Shuyang, et al.
Publicado: (2026)

Do Androids Know They're Only Dreaming of Electric Sheep?
por: CH-Wang, Sky, et al.
Publicado: (2023)

Reasoning Pattern Matters: Learning to Reason without Human Rationales
por: Pang, Chaoxu, et al.
Publicado: (2025)

GNN2R: Weakly-Supervised Rationale-Providing Question Answering over Knowledge Graphs
por: Wang, Ruijie, et al.
Publicado: (2023)

SIM-CoT: Supervised Implicit Chain-of-Thought
por: Wei, Xilin, et al.
Publicado: (2025)

Enhancing Relation Extraction via Supervised Rationale Verification and Feedback
por: Li, Yongqi, et al.
Publicado: (2024)

Process Supervision of Confidence Margin for Calibrated LLM Reasoning
por: Wang, Liaoyaqi, et al.
Publicado: (2026)

OpenAI Cribbed Our Tax Example, But Can GPT-4 Really Do Tax?
por: Blair-Stanek, Andrew, et al.
Publicado: (2023)

Structural Rationale Distillation via Reasoning Space Compression
por: Yang, Jialin, et al.
Publicado: (2026)

TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning
por: Sanders, Kate, et al.
Publicado: (2024)

LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error
por: Wang, Boshi, et al.
Publicado: (2024)

Conformal Thinking: Risk Control for Reasoning on a Compute Budget
por: Wang, Xi, et al.
Publicado: (2026)