Imagen de Portada

When Models Reason in Your Language: Controlling Thinking Language Comes at the Cost of Accuracy

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Qi, Jirui, Chen, Shan, Xiong, Zidi, Fernández, Raquel, Bitterman, Danielle S., Bisazza, Arianna
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

Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models
por: Qi, Jirui, et al.
Publicado: (2023)

On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation
por: Qi, Jirui, et al.
Publicado: (2025)

Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation
por: Qi, Jirui, et al.
Publicado: (2024)

Post-Training Language Models for Crosslingual Consistency
por: Liu, Tianyu, et al.
Publicado: (2026)

The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Models
por: Chen, Xinyi, et al.
Publicado: (2024)

Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization
por: Neplenbroek, Vera, et al.
Publicado: (2025)

MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs
por: Neplenbroek, Vera, et al.
Publicado: (2024)

Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation
por: Neplenbroek, Vera, et al.
Publicado: (2024)

Proof of Time: A Benchmark for Evaluating Scientific Idea Judgments
por: Ye, Bingyang, et al.
Publicado: (2026)

Assessing the Impact of Typological Features on Multilingual Machine Translation in the Age of Large Language Models
por: Hirak, Vitalii, et al.
Publicado: (2026)

Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models
por: Padovani, Francesca, et al.
Publicado: (2025)

debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias
por: Sasse, Kuleen, et al.
Publicado: (2024)

NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communication
por: Lian, Yuchen, et al.
Publicado: (2024)

Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation
por: Liu, Tianyu, et al.
Publicado: (2024)

A Primer on the Inner Workings of Transformer-based Language Models
por: Ferrando, Javier, et al.
Publicado: (2024)

Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses
por: Sarti, Gabriele, et al.
Publicado: (2024)

A Unified Assessment of the Poverty of the Stimulus Argument for Neural Language Models
por: Yang, Xiulin, et al.
Publicado: (2026)

Is Child-Directed Language Optimized for Word Learning? A Computational Study of Verb Meaning Acquisition
por: Padovani, Francesca, et al.
Publicado: (2026)

BabyLM Challenge: Exploring the Effect of Variation Sets on Language Model Training Efficiency
por: Haga, Akari, et al.
Publicado: (2024)

Can Language Models Identify Side Effects of Breast Cancer Radiation Treatments?
por: Seah, Natalie, et al.
Publicado: (2026)

KScope: A Framework for Characterizing the Knowledge Status of Language Models
por: Xiao, Yuxin, et al.
Publicado: (2025)

Steering Large Language Models for Machine Translation Personalization
por: Scalena, Daniel, et al.
Publicado: (2025)

When Raw Data Prevails: Are Large Language Model Embeddings Effective in Numerical Data Representation for Medical Machine Learning Applications?
por: Gao, Yanjun, et al.
Publicado: (2024)

Improving Clinical NLP Performance through Language Model-Generated Synthetic Clinical Data
por: Chen, Shan, et al.
Publicado: (2024)

NeLLCom-Lex: A Neural-agent Framework to Study the Interplay between Lexical Systems and Language Use
por: Zhang, Yuqing, et al.
Publicado: (2025)

Simulating the Emergence of Differential Case Marking with Communicating Neural-Network Agents
por: Lian, Yuchen, et al.
Publicado: (2025)

Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation
por: Chen, Shan, et al.
Publicado: (2024)

Evaluation of ChatGPT Family of Models for Biomedical Reasoning and Classification
por: Chen, Shan, et al.
Publicado: (2023)

Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks
por: Gallifant, Jack, et al.
Publicado: (2024)

ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models
por: He, Qianyu, et al.
Publicado: (2025)

Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
por: Xiong, Zidi, et al.
Publicado: (2025)

Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training
por: Yao, Yihang, et al.
Publicado: (2025)

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

MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs
por: Jumelet, Jaap, et al.
Publicado: (2025)

Modeling Human-Like Color Naming Behavior in Context
por: Zhang, Yuqing, et al.
Publicado: (2026)

Cognitive Decision Routing in Large Language Models: When to Think Fast, When to Think Slow
por: Du, Y., et al.
Publicado: (2025)

Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts
por: Du, Hanwen, et al.
Publicado: (2025)

When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment
por: Yan, Hanqi, et al.
Publicado: (2025)

AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control
por: Li, Ruosen, et al.
Publicado: (2025)

Position Paper On Diagnostic Uncertainty Estimation from Large Language Models: Next-Word Probability Is Not Pre-test Probability
por: Gao, Yanjun, et al.
Publicado: (2024)