Imagen de Portada

What Really Counts? Examining Step and Token Level Attribution in Multilingual CoT Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ferrao, Jeremias, Basar, Ezgi, Islam, Khondoker Ittehadul, Hassani, Mahrokh
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Reveal-Bangla: A Dataset for Cross-Lingual Multi-Step Reasoning Evaluation
por: Islam, Khondoker Ittehadul, et al.
Publicado: (2025)

Leveraging Sentiment for Offensive Text Classification
por: Islam, Khondoker Ittehadul
Publicado: (2024)

Joint Effects of Argumentation Theory, Audio Modality and Data Enrichment on LLM-Based Fallacy Classification
por: Zhou, Hongxu, et al.
Publicado: (2025)

Improving OCR for Historical Texts of Multiple Languages
por: Westerdijk, Hylke, et al.
Publicado: (2025)

Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step
por: Wang, Zezhong, et al.
Publicado: (2024)

From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
por: Deng, Yuntian, et al.
Publicado: (2024)

Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning
por: Jin, Senjie, et al.
Publicado: (2025)

Investigating CoT Monitorability in Large Reasoning Models
por: Yang, Shu, et al.
Publicado: (2025)

Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
por: Wu, Jiawei, et al.
Publicado: (2026)

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
por: Li, Li, et al.
Publicado: (2025)

Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
por: Luo, Haotian, et al.
Publicado: (2025)

CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning
por: Feng, Kehua, et al.
Publicado: (2025)

D-SCoRE: Document-Centric Segmentation and CoT Reasoning with Structured Export for QA-CoT Data Generation
por: Zhou, Weibo, et al.
Publicado: (2025)

Efficient Long CoT Reasoning in Small Language Models
por: Wang, Zhaoyang, et al.
Publicado: (2025)

TurBLiMP: A Turkish Benchmark of Linguistic Minimal Pairs
por: Başar, Ezgi, et al.
Publicado: (2025)

Do LLMs Really Think Step-by-step In Implicit Reasoning?
por: Yu, Yijiong
Publicado: (2024)

Exploring the Limitations of Mamba in COPY and CoT Reasoning
por: Ren, Ruifeng, et al.
Publicado: (2024)

Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
por: Guo, Ziyu, et al.
Publicado: (2025)

CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning
por: Dong, Qihua, et al.
Publicado: (2025)

KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning
por: Mondal, Debjyoti, et al.
Publicado: (2024)

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
por: Yan, Shaotian, et al.
Publicado: (2026)

TokenShapley: Token Level Context Attribution with Shapley Value
por: Xiao, Yingtai, et al.
Publicado: (2025)

Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning
por: Zhao, Shangziqi, et al.
Publicado: (2025)

Co-CoT: A Prompt-Based Framework for Collaborative Chain-of-Thought Reasoning
por: Yoo, Seunghyun
Publicado: (2025)

Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery
por: Li, Jiatong, et al.
Publicado: (2025)

Long or short CoT? Investigating Instance-level Switch of Large Reasoning Models
por: Zhang, Ruiqi, et al.
Publicado: (2025)

Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding
por: Wang, Yifei
Publicado: (2025)

Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL
por: Dai, Yaxun, et al.
Publicado: (2026)

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning
por: Li, Ang, et al.
Publicado: (2025)

Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning
por: Yang, Cehao, et al.
Publicado: (2025)

CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process
por: Bi, Jinhe, et al.
Publicado: (2025)

Investigating Mysteries of CoT-Augmented Distillation
por: Wadhwa, Somin, et al.
Publicado: (2024)

GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification
por: Wan, Faxian, et al.
Publicado: (2026)

Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
por: Puerto, Haritz, et al.
Publicado: (2024)

CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation
por: Tong, Zhao, et al.
Publicado: (2026)

S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs
por: Du, Yanrui, et al.
Publicado: (2026)

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
por: Sprague, Zayne, et al.
Publicado: (2024)

How Likely Do LLMs with CoT Mimic Human Reasoning?
por: Bao, Guangsheng, et al.
Publicado: (2024)

What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code
por: Zhao, Yuze, et al.
Publicado: (2026)

From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning
por: Purohit, Kiran, et al.
Publicado: (2026)