Imagen de Portada

Do LLMs Signal When They're Right? Evidence from Neuron Agreement

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Kang, Wang, Yaoning, Xiong, Kai, Feng, Zhuoka, Sun, Wenhe, Chen, Haotian, Cao, Yixin
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

Thinking Out Loud: Do Reasoning Models Know When They're Right?
por: Zeng, Qingcheng, et al.
Publicado: (2025)

Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification
por: Zhang, Anqi, et al.
Publicado: (2025)

Do Language Models Know When They're Hallucinating References?
por: Agrawal, Ayush, et al.
Publicado: (2023)

NEX: Neuron Explore-Exploit Scoring for Label-Free Chain-of-Thought Selection and Model Ranking
por: Chen, Kang, et al.
Publicado: (2026)

Do Androids Know They're Only Dreaming of Electric Sheep?
por: CH-Wang, Sky, et al.
Publicado: (2023)

ARM: Role-Conditioned Neuron Transplantation for Training-Free Generalist LLM Agent Merging
por: Feng, Zhuoka, et al.
Publicado: (2026)

Model Utility Law: Evaluating LLMs beyond Performance through Mechanism Interpretable Metric
por: Cao, Yixin, et al.
Publicado: (2025)

Thinking Traps in Long Chain-of-Thought: A Measurable Study and Trap-Aware Adaptive Restart
por: Chen, Kang, et al.
Publicado: (2026)

Cogs in a Machine, Doing What They're Meant to Do -- The AMI Submission to the WMT24 General Translation Task
por: Jasonarson, Atli, et al.
Publicado: (2024)

EffiEval: Efficient and Generalizable Model Evaluation via Capability Coverage Maximization
por: Wang, Yaoning, et al.
Publicado: (2025)

Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer
por: Cui, Chenhang, et al.
Publicado: (2026)

Do Small Language Models Know When They're Wrong? Confidence-Based Cascade Scoring for Educational Assessment
por: Burleigh, Tyler
Publicado: (2026)

Less Data Less Tokens: Multilingual Unification Learning for Efficient Test-Time Reasoning in LLMs
por: Chen, Kang, et al.
Publicado: (2025)

Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs
por: Pan, Haowen, et al.
Publicado: (2025)

Do Hallucination Neurons Generalize? Evidence from Cross-Domain Transfer in LLMs
por: Vaddi, Snehit, et al.
Publicado: (2026)

Intuitive or Dependent? Investigating LLMs' Behavior Style to Conflicting Prompts
por: Ying, Jiahao, et al.
Publicado: (2023)

H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
por: Gao, Cheng, et al.
Publicado: (2025)

Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers
por: Pan, Haowen, et al.
Publicado: (2023)

The Realignment Problem: When Right becomes Wrong in LLMs
por: Sharma, Aakash Sen, et al.
Publicado: (2025)

The Knowledge Microscope: Features as Better Analytical Lenses than Neurons
por: Chen, Yuheng, et al.
Publicado: (2025)

Do LLMs Know What Is Private Internally? Probing and Steering Contextual Privacy Norms in Large Language Model Representations
por: Wang, Haoran, et al.
Publicado: (2026)

Readability-guided Idiom-aware Sentence Simplification (RISS) for Chinese
por: Zhang, Jingshen, et al.
Publicado: (2024)

Long Context vs. RAG for LLMs: An Evaluation and Revisits
por: Li, Xinze, et al.
Publicado: (2024)

Do LLMs Encode Frame Semantics? Evidence from Frame Identification
por: Chundru, Jayanth Krishna, et al.
Publicado: (2025)

When Do Language Models Endorse Limitations on Human Rights Principles?
por: Samway, Keenan, et al.
Publicado: (2026)

Dissecting Role Cognition in Medical LLMs via Neuronal Ablation
por: Liang, Xun, et al.
Publicado: (2025)

"Yeah Right!" -- Do LLMs Exhibit Multimodal Feature Transfer?
por: Reichman, Benjamin, et al.
Publicado: (2025)

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation
por: Yu, Ye, et al.
Publicado: (2026)

MEMLA: Enhancing Multilingual Knowledge Editing with Neuron-Masked Low-Rank Adaptation
por: Xie, Jiakuan, et al.
Publicado: (2024)

Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
por: Zhang, Zhuoxuan, et al.
Publicado: (2025)

Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning
por: Xiong, Kai, et al.
Publicado: (2024)

PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models
por: Yu, Ye, et al.
Publicado: (2025)

One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models
por: Cao, Pengfei, et al.
Publicado: (2024)

Empathy and the Right to Be an Exception: What LLMs Can and Cannot Do
por: Kidder, William, et al.
Publicado: (2024)

LLM Reasoning Predicts When Models Are Right: Evidence from Coding Classroom Discourse
por: Ahtisham, Bakhtawar, et al.
Publicado: (2026)

When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation
por: Ni, Shiyu, et al.
Publicado: (2024)

Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models
por: Chen, Yuheng, et al.
Publicado: (2024)

White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMs
por: Wan, Yixin, et al.
Publicado: (2024)

Do the Right Thing, Just Debias! Multi-Category Bias Mitigation Using LLMs
por: Roy, Amartya, et al.
Publicado: (2024)

LANDeRMT: Detecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation
por: Zhu, Shaolin, et al.
Publicado: (2024)