Imagen de Portada

Thinking beyond the anthropomorphic paradigm benefits LLM research

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ibrahim, Lujain, Cheng, Myra
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

ELEPHANT: Measuring and understanding social sycophancy in LLMs
por: Cheng, Myra, et al.
Publicado: (2025)

Training language models to be warm and empathetic makes them less reliable and more sycophantic
por: Ibrahim, Lujain, et al.
Publicado: (2025)

Verbalizing LLMs' assumptions to explain and control sycophancy
por: Cheng, Myra, et al.
Publicado: (2026)

What is the social benefit of hate speech detection research? A Systematic Review
por: Wong, Sidney Gig-Jan
Publicado: (2024)

Deconstructing sentence disambiguation by joint latent modeling of reading paradigms: LLM surprisal is not enough
por: Paape, Dario, et al.
Publicado: (2026)

Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
por: Tan, Wenhui, et al.
Publicado: (2025)

Offloading Score: Measuring AI Reliance Through Counterfactual Workflows
por: Padmakumar, Vishakh, et al.
Publicado: (2026)

A Reality check of the benefits of LLM in business
por: Cheung, Ming
Publicado: (2024)

Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking
por: Tian, Xiaoyu, et al.
Publicado: (2025)

Could Thinking Multilingually Empower LLM Reasoning?
por: Gao, Changjiang, et al.
Publicado: (2025)

Think-J: Learning to Think for Generative LLM-as-a-Judge
por: Huang, Hui, et al.
Publicado: (2025)

Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens
por: Chen, Wei-Lin, et al.
Publicado: (2026)

Thinking Makes LLM Agents Introverted: How Mandatory Thinking Can Backfire in User-Engaged Agents
por: Li, Jiatong, et al.
Publicado: (2026)

Steering LLM Thinking with Budget Guidance
por: Li, Junyan, et al.
Publicado: (2025)

Thinkless: LLM Learns When to Think
por: Fang, Gongfan, et al.
Publicado: (2025)

Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations
por: Yu, Sunny, et al.
Publicado: (2025)

Thinking Machines: A Survey of LLM based Reasoning Strategies
por: Bandyopadhyay, Dibyanayan, et al.
Publicado: (2025)

Latent Debate: A Surrogate Framework for Interpreting LLM Thinking
por: Chen, Lihu, et al.
Publicado: (2025)

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains
por: Xie, Hui, et al.
Publicado: (2026)

Escaping the sentence-level paradigm in machine translation
por: Post, Matt, et al.
Publicado: (2023)

Thinking Fast, Thinking Wrong: Intuitiveness Modulates LLM Counterfactual Reasoning in Policy Evaluation
por: He, Yanjie
Publicado: (2026)

Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking
por: Cheng, Xiaoxue, et al.
Publicado: (2025)

"Well, Keep Thinking": Enhancing LLM Reasoning with Adaptive Injection Decoding
por: Jin, Hyunbin, et al.
Publicado: (2025)

SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens
por: Dragunov, Nikita, et al.
Publicado: (2025)

Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning
por: Zhao, Haodong, et al.
Publicado: (2025)

ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning
por: Huang, Shulin, et al.
Publicado: (2025)

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning
por: Wei, Jiaqi, et al.
Publicado: (2026)

ThinkSwitcher: When to Think Hard, When to Think Fast
por: Liang, Guosheng, et al.
Publicado: (2025)

LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens
por: Zebaze, Armel, et al.
Publicado: (2025)

SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking
por: Liu, Junnan, et al.
Publicado: (2025)

Beyond One Path: Evaluating and Enhancing Divergent Thinking in Interactive LLM Agents
por: Park, Jihyeong, et al.
Publicado: (2026)

The benefits of query-based KGQA systems for complex and temporal questions in LLM era
por: Alekseev, Artem, et al.
Publicado: (2025)

ALRM: Agentic LLM for Robotic Manipulation
por: Santos, Vitor Gaboardi dos, et al.
Publicado: (2026)

Toward LLM-Supported Automated Assessment of Critical Thinking Subskills
por: Peczuh, Marisa C., et al.
Publicado: (2025)

ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection
por: Gao, Changjiang, et al.
Publicado: (2026)

Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
por: Saha, Swarnadeep, et al.
Publicado: (2025)

Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning
por: Tang, Lexiang, et al.
Publicado: (2026)

HumT DumT: Measuring and controlling human-like language in LLMs
por: Cheng, Myra, et al.
Publicado: (2025)

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

EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models
por: Cheng, Sijie, et al.
Publicado: (2023)