Cover Image

Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zbeeb, Mohammad, Hammoud, Hasan Abed Al Kader, Ghanem, Bernard
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2025)

Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2025)

AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models
by: Zbeeb, Mohammad, et al.
Published: (2025)

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

TAPS: Task Aware Proposal Distributions for Speculative Sampling
by: Zbib, Mohamad, et al.
Published: (2026)

DiffCLIP: Differential Attention Meets CLIP
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2025)

Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection
by: Shairah, Harethah Abu, et al.
Published: (2025)

An Embarrassingly Simple Defense Against LLM Abliteration Attacks
by: Shairah, Harethah Abu, et al.
Published: (2025)

Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning
by: Alssum, Lama, et al.
Published: (2025)

Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2024)

On the Importance of Pretraining Data Alignment for Atomic Property Prediction
by: Ghunaim, Yasir, et al.
Published: (2025)

Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning
by: Alssum, Lama, et al.
Published: (2025)

On Pretraining Data Diversity for Self-Supervised Learning
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2024)

SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2024)

QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation
by: Slim, Ali, et al.
Published: (2026)

Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought
by: Chen, Qiguang, et al.
Published: (2024)

SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
by: Jiang, Fengqing, et al.
Published: (2025)

Logit-Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning
by: Quamar, Mohammad Atif, et al.
Published: (2025)

Effectiveness of Chain-of-Thought in Distilling Reasoning Capability from Large Language Models
by: Do, Cong-Thanh, et al.
Published: (2025)

Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering
by: Tang, Xinyu, et al.
Published: (2025)

Efficient Reasoning via Chain of Unconscious Thought
by: Gong, Ruihan, et al.
Published: (2025)

Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models
by: Cheng, Xinyuan, et al.
Published: (2026)

Short Chains, Deep Thoughts: Balancing Reasoning Efficiency and Intra-Segment Capability via Split-Merge Optimization
by: Gui, Runquan, et al.
Published: (2026)

Faithful Logical Reasoning via Symbolic Chain-of-Thought
by: Xu, Jundong, et al.
Published: (2024)

L2V-CoT: Cross-Modal Transfer of Chain-of-Thought Reasoning via Latent Intervention
by: Zhan, Yuliang, et al.
Published: (2025)

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning
by: Chen, Qiguang, et al.
Published: (2025)

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
by: Zhang, Yunxiang, et al.
Published: (2025)

Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions
by: Ranaldi, Leonardo, et al.
Published: (2025)

Chain-of-Thought Reasoning Without Prompting
by: Wang, Xuezhi, et al.
Published: (2024)

MeXtract: Light-Weight Metadata Extraction from Scientific Papers
by: Alyafeai, Zaid, et al.
Published: (2025)

MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs
by: Alyafeai, Zaid, et al.
Published: (2025)

From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web
by: Prabhu, Ameya, et al.
Published: (2023)

Scalable Chain of Thoughts via Elastic Reasoning
by: Xu, Yuhui, et al.
Published: (2025)

Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning
by: Lin, Jingyang, et al.
Published: (2025)

Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models
by: Yao, Yao, et al.
Published: (2023)

Reliable Chain-of-Thought via Prefix Consistency
by: Iwase, Naoto, et al.
Published: (2026)

Uncovering Latent Chain of Thought Vectors in Language Models
by: Zhang, Jason, et al.
Published: (2024)

On the Impact of Fine-Tuning on Chain-of-Thought Reasoning
by: Lobo, Elita, et al.
Published: (2024)

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
by: Zhang, Yunxiang, et al.
Published: (2025)

Binder: Hierarchical Concept Representation through Order Embedding of Binary Vectors
by: Gyurek, Croix, et al.
Published: (2024)