Buchumschlag

Think, But Don't Overthink: Reproducing Recursive Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
1. Verfasser:	Wang, Daren
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
von: Hassid, Michael, et al.
Veröffentlicht: (2025)

Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?
von: Jedidi, Nour, et al.
Veröffentlicht: (2025)

Reasoning Models Don't Just Think Longer, They Move Differently
von: Gjølbye, Anders, et al.
Veröffentlicht: (2026)

Reasoning Models Don't Always Say What They Think
von: Chen, Yanda, et al.
Veröffentlicht: (2025)

Don't Overthink It: Inter-Rollout Action Agreement as a Free Adaptive-Compute Signal for LLM Agents
von: Sethi, Khushal
Veröffentlicht: (2026)

Don't Think Twice! Over-Reasoning Impairs Confidence Calibration
von: Lacombe, Romain, et al.
Veröffentlicht: (2025)

Language Models Don't Learn the Physical Manifestation of Language
von: Lee, Bruce W., et al.
Veröffentlicht: (2024)

Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency
von: Wang, Chenlong, et al.
Veröffentlicht: (2025)

Don't Throw Away Your Pretrained Model
von: Feng, Shangbin, et al.
Veröffentlicht: (2025)

Don't Think of the White Bear: Ironic Negation in Transformer Models Under Cognitive Load
von: Mann, Logan, et al.
Veröffentlicht: (2025)

Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Models
von: Huang, Zemin, et al.
Veröffentlicht: (2025)

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
von: Chen, Xingyu, et al.
Veröffentlicht: (2024)

Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Tasks
von: Chochlakis, Georgios, et al.
Veröffentlicht: (2024)

R-Tuning: Instructing Large Language Models to Say `I Don't Know'
von: Zhang, Hanning, et al.
Veröffentlicht: (2023)

Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models
von: Parmar, Jupinder, et al.
Veröffentlicht: (2024)

Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models
von: Lee, Jonggeun, et al.
Veröffentlicht: (2025)

Do Retrieval Augmented Language Models Know When They Don't Know?
von: Zhou, Youchao, et al.
Veröffentlicht: (2025)

Don't Touch My Diacritics
von: Gorman, Kyle, et al.
Veröffentlicht: (2024)

Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Large Language Models
von: Yao, Lin
Veröffentlicht: (2026)

Tell, Don't Show: Leveraging Language Models' Abstractive Retellings to Model Literary Themes
von: Lucy, Li, et al.
Veröffentlicht: (2025)

Don't Pay Attention
von: Hammoud, Mohammad, et al.
Veröffentlicht: (2025)

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
von: Sui, Yang, et al.
Veröffentlicht: (2025)

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?
von: Fan, Chenrui, et al.
Veröffentlicht: (2025)

Fine-Tune, Don't Prompt, Your Language Model to Identify Biased Language in Clinical Notes
von: Landi, Isotta, et al.
Veröffentlicht: (2026)

Sample, Don't Search: Rethinking Test-Time Alignment for Language Models
von: Faria, Gonçalo, et al.
Veröffentlicht: (2025)

Don't Say No: Jailbreaking LLM by Suppressing Refusal
von: Zhou, Yukai, et al.
Veröffentlicht: (2024)

Don't Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models
von: Li, Jinzhe, et al.
Veröffentlicht: (2025)

Reasoning Models Reason Well, Until They Don't
von: Rameshkumar, Revanth, et al.
Veröffentlicht: (2025)

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models
von: Pu, Xiao, et al.
Veröffentlicht: (2025)

DRQA: Dynamic Reasoning Quota Allocation for Controlling Overthinking in Reasoning Large Language Models
von: Yan, Kaiwen, et al.
Veröffentlicht: (2025)

Don't Change My View: Ideological Bias Auditing in Large Language Models
von: Kröger, Paul, et al.
Veröffentlicht: (2025)

Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models
von: Yu, Zhiyuan, et al.
Veröffentlicht: (2024)

Batch Prompting Suppresses Overthinking Reasoning Under Constraint: How Batch Prompting Suppresses Overthinking in Reasoning Models
von: Srivastava, Saurabh, et al.
Veröffentlicht: (2025)

If You Don't Understand It, Don't Use It: Eliminating Trojans with Filters Between Layers
von: Hernandez, Adriano
Veröffentlicht: (2024)

Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models
von: Yu, Longxuan, et al.
Veröffentlicht: (2026)

Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models
von: Srivastava, Gaurav, et al.
Veröffentlicht: (2025)

Large Language Models Must Be Taught to Know What They Don't Know
von: Kapoor, Sanyam, et al.
Veröffentlicht: (2024)

Don't Erase, Inform! Detecting and Contextualizing Harmful Language in Cultural Heritage Collections
von: Mastromichalakis, Orfeas Menis, et al.
Veröffentlicht: (2025)

Don't Learn, Ground: A Case for Natural Language Inference with Visual Grounding
von: Ignatev, Daniil, et al.
Veröffentlicht: (2025)

Don't Command, Cultivate: An Exploratory Study of System-2 Alignment
von: Wang, Yuhang, et al.
Veröffentlicht: (2024)