Copertina

Truth Neurons

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Haohang, Cao, Yupeng, Yu, Yangyang, Suchow, Jordan W., Zhu, Zining
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Can AI Validate Science? Benchmarking LLMs for Accurate Scientific Claim $\rightarrow$ Evidence Reasoning
di: Javaji, Shashidhar Reddy, et al.
Pubblicazione: (2025)

FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks
di: Cao, Yupeng, et al.
Pubblicazione: (2026)

Replicating Human Social Perception in Generative AI: Evaluating the Valence-Dominance Model
di: Gurkan, Necdet, et al.
Pubblicazione: (2025)

Evaluating Large Language Models on the GMAT: Implications for the Future of Business Education
di: Ashrafimoghari, Vahid, et al.
Pubblicazione: (2024)

FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making
di: Yu, Yangyang, et al.
Pubblicazione: (2024)

What does the Knowledge Neuron Thesis Have to do with Knowledge?
di: Niu, Jingcheng, et al.
Pubblicazione: (2024)

INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent
di: Li, Haohang, et al.
Pubblicazione: (2024)

On Higher Order Busy Beaver Function
di: Cao, Zining
Pubblicazione: (2025)

Exploring Public Opinion on Responsible AI Through The Lens of Cultural Consensus Theory
di: Gurkan, Necdet, et al.
Pubblicazione: (2024)

MERMAID: Memory-Enhanced Retrieval and Reasoning with Multi-Agent Iterative Knowledge Grounding for Veracity Assessment
di: Cao, Yupeng, et al.
Pubblicazione: (2026)

Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce
di: Wang, Haojin, et al.
Pubblicazione: (2025)

Understanding Language Model Circuits through Knowledge Editing
di: Ge, Huaizhi, et al.
Pubblicazione: (2024)

How Well Can Knowledge Edit Methods Edit Perplexing Knowledge?
di: Ge, Huaizhi, et al.
Pubblicazione: (2024)

Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agents
di: He, Haorui, et al.
Pubblicazione: (2025)

Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs
di: Fu, Yao, et al.
Pubblicazione: (2025)

TruthFlow: Truthful LLM Generation via Representation Flow Correction
di: Wang, Hanyu, et al.
Pubblicazione: (2025)

Scenarios and Approaches for Situated Natural Language Explanations
di: Qiu, Pengshuo, et al.
Pubblicazione: (2024)

When Agents Trade: Live Multi-Market Trading Benchmark for LLM Agents
di: Qian, Lingfei, et al.
Pubblicazione: (2025)

Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers
di: Xin, Rihui, et al.
Pubblicazione: (2025)

What Would You Ask When You First Saw $a^2+b^2=c^2$? Evaluating LLM on Curiosity-Driven Questioning
di: Javaji, Shashidhar Reddy, et al.
Pubblicazione: (2024)

LLM-Generated Black-box Explanations Can Be Adversarially Helpful
di: Ajwani, Rohan, et al.
Pubblicazione: (2024)

On the Universal Truthfulness Hyperplane Inside LLMs
di: Liu, Junteng, et al.
Pubblicazione: (2024)

Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity
di: Yu, Lei, et al.
Pubblicazione: (2024)

Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs
di: Jaipersaud, Brandon, et al.
Pubblicazione: (2024)

Improving Generalization in LLM Structured Pruning via Function-Aware Neuron Grouping
di: Yu, Tao, et al.
Pubblicazione: (2025)

TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs
di: Yaldiz, Duygu Nur, et al.
Pubblicazione: (2025)

Truth Knows No Language: Evaluating Truthfulness Beyond English
di: Figueras, Blanca Calvo, et al.
Pubblicazione: (2025)

NeuronMoE: Neuron-Guided Mixture-of-Experts for Efficient Multilingual LLM Extension
di: Li, Rongzhi, et al.
Pubblicazione: (2026)

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
di: Zhang, Shaolei, et al.
Pubblicazione: (2024)

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

Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong
di: Si, Chenglei, et al.
Pubblicazione: (2023)

TruthStance: An Annotated Dataset of Conversations on Truth Social
di: Ameen, Fathima, et al.
Pubblicazione: (2026)

Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering
di: Zheng, Li, et al.
Pubblicazione: (2026)

Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis
di: Zhu, Kejian, et al.
Pubblicazione: (2025)

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

TruthEval: A Dataset to Evaluate LLM Truthfulness and Reliability
di: Khatun, Aisha, et al.
Pubblicazione: (2024)

Meaning Beyond Truth Conditions: Evaluating Discourse Level Understanding via Anaphora Accessibility
di: Zhu, Xiaomeng, et al.
Pubblicazione: (2025)

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

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
di: Wei, Zhepei, et al.
Pubblicazione: (2025)

Understanding the Effects of Iterative Prompting on Truthfulness
di: Krishna, Satyapriya, et al.
Pubblicazione: (2024)