Cover Image

Select to Think: Unlocking SLM Potential with Local Sufficiency

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ye, Wenxuan, Zhang, Yangyang, An, Xueli, Carle, Georg, Ma, Yunpu
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FedABC: Attention-Based Client Selection for Federated Learning with Long-Term View
by: Ye, Wenxuan, et al.
Published: (2025)

StreamingThinker: Large Language Models Can Think While Reading
by: Tong, Junlong, et al.
Published: (2025)

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
by: Zhang, Zhen, et al.
Published: (2025)

Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding
by: Bergner, Benjamin, et al.
Published: (2024)

When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning
by: Xiang, Yang, et al.
Published: (2026)

Unlocking Recursive Thinking of LLMs: Alignment via Refinement
by: Zhang, Haoke, et al.
Published: (2025)

Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning
by: Zhang, Xue, et al.
Published: (2025)

From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs
by: He, Jie, et al.
Published: (2025)

SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL
by: Qu, Ge, et al.
Published: (2025)

Towards a Larger Model via One-Shot Federated Learning on Heterogeneous Client Models
by: Ye, Wenxuan, et al.
Published: (2025)

Unlocking Structured Thinking in Language Models with Cognitive Prompting
by: Kramer, Oliver, et al.
Published: (2024)

Enhancing SLM via ChatGPT and Dataset Augmentation
by: Pieper, Tom, et al.
Published: (2024)

GmSLM : Generative Marmoset Spoken Language Modeling
by: Sternberg, Talia, et al.
Published: (2025)

Unlocking the Potential of Model Merging for Low-Resource Languages
by: Tao, Mingxu, et al.
Published: (2024)

Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
by: Gekhman, Zorik, et al.
Published: (2026)

CorrectionLM: Self-Corrections with SLM for Dialogue State Tracking
by: Lee, Chia-Hsuan, et al.
Published: (2024)

Advancing SLM Tool-Use Capability using Reinforcement Learning
by: Paprunia, Dhruvi, et al.
Published: (2025)

SLM-SQL: An Exploration of Small Language Models for Text-to-SQL
by: Sheng, Lei, et al.
Published: (2025)

Zero Token-Driven Deep Thinking in LLMs: Unlocking the Full Potential of Existing Parameters via Cyclic Refinement
by: Li, Guanghao, et al.
Published: (2025)

LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors
by: Ma, Rao, et al.
Published: (2025)

RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generation
by: Xu, Zhichao, et al.
Published: (2025)

SLM-Mod: Small Language Models Surpass LLMs at Content Moderation
by: Zhan, Xianyang, et al.
Published: (2024)

Rethinking the Role of LLMs in Time Series Forecasting
by: Qiu, Xin, et al.
Published: (2026)

Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modeling
by: Chou, Ju-Chieh, et al.
Published: (2025)

PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection
by: Bi, Jinhe, et al.
Published: (2025)

The Eloquence team submission for task 1 of MLC-SLM challenge
by: Concina, Lorenzo, et al.
Published: (2025)

SLM as Guardian: Pioneering AI Safety with Small Language Models
by: Kwon, Ohjoon, et al.
Published: (2024)

NTU Speechlab LLM-Based Multilingual ASR System for Interspeech MLC-SLM Challenge 2025
by: Peng, Yizhou, et al.
Published: (2025)

Bridge-Coder: Unlocking LLMs' Potential to Overcome Language Gaps in Low-Resource Code
by: Zhang, Jipeng, et al.
Published: (2024)

ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge
by: Taghavi, Zeinab Sadat, et al.
Published: (2025)

ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails
by: Wen, Xiaofei, et al.
Published: (2025)

Reasoning Path Divergence: A New Metric and Curation Strategy to Unlock LLM Diverse Thinking
by: Ju, Feng, et al.
Published: (2025)

Q-Mirror: Unlocking the Multi-Modal Potential of Scientific Text-Only QA Pairs
by: Wang, Junying, et al.
Published: (2025)

Unlocking a New Rust Programming Experience: Fast and Slow Thinking with LLMs to Conquer Undefined Behaviors
by: Jiang, Renshuang, et al.
Published: (2025)

Kuwain 1.5B: An Arabic SLM via Language Injection
by: Hennara, Khalil, et al.
Published: (2025)

Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causes
by: Wang, Mingyang, et al.
Published: (2025)

Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design
by: Guo, Xu, et al.
Published: (2026)

Improving LLM Reasoning through Interpretable Role-Playing Steering
by: Wang, Anyi, et al.
Published: (2025)

The Few Govern the Many:Unveiling Few-Layer Dominance for Time Series Models
by: Qiu, Xin, et al.
Published: (2025)

ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
by: Wang, Yujun, et al.
Published: (2025)