Image de couverture de livre

AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sheshadri, Abhay, Ewart, Aidan, Fronsdal, Kai, Gupta, Isha, Bowman, Samuel R., Price, Sara, Marks, Samuel, Wang, Rowan
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
par: Guo, Phillip, et autres
Publié: (2024)

Liars' Bench: Evaluating Lie Detectors for Language Models
par: Kretschmar, Kieron, et autres
Publié: (2025)

DECOR: Auditing LLM Deception via Information Manipulation Theory
par: Cai, Linyue, et autres
Publié: (2026)

MISR: Measuring Instrumental Self-Reasoning in Frontier Models
par: Fronsdal, Kai, et autres
Publié: (2024)

Let's Think Dot by Dot: Hidden Computation in Transformer Language Models
par: Pfau, Jacob, et autres
Publié: (2024)

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
par: Sheshadri, Abhay, et autres
Publié: (2024)

Auditing language models for hidden objectives
par: Marks, Samuel, et autres
Publié: (2025)

Introspection Adapters: Training LLMs to Report Their Learned Behaviors
par: Shenoy, Keshav, et autres
Publié: (2026)

Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias
par: Sakhawat, Adib, et autres
Publié: (2026)

BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks
par: Tu, Xinming, et autres
Publié: (2026)

AuditWen:An Open-Source Large Language Model for Audit
par: Huang, Jiajia, et autres
Publié: (2024)

LLM Evaluators Recognize and Favor Their Own Generations
par: Panickssery, Arjun, et autres
Publié: (2024)

Audited Reasoning Refinement: Fine-Tuning Language Models via LLM-Guided Step-Wise Evaluation and Correction
par: Bhattacharyya, Sumanta, et autres
Publié: (2025)

What Artificial Neural Networks Can Tell Us About Human Language Acquisition
par: Warstadt, Alex, et autres
Publié: (2022)

An Audit on the Perspectives and Challenges of Hallucinations in NLP
par: Venkit, Pranav Narayanan, et autres
Publié: (2024)

Market-Bench: Evaluating Large Language Models on Introductory Quantitative Trading and Market Dynamics
par: Srivastava, Abhay, et autres
Publié: (2025)

Audit, Alignment, and Optimization of LM-Powered Subroutines with Application to Public Comment Processing
par: Raab, Reilly, et autres
Publié: (2025)

Eight Methods to Evaluate Robust Unlearning in LLMs
par: Lynch, Aengus, et autres
Publié: (2024)

GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence
par: Krishna, Kundan, et autres
Publié: (2024)

AuditGPT: Auditing Smart Contracts with ChatGPT
par: Xia, Shihao, et autres
Publié: (2024)

Code Comprehension then Auditing for Unsupervised LLM Evaluation
par: Patel, Bhrij, et autres
Publié: (2024)

Model Spec Midtraining: Improving How Alignment Training Generalizes
par: Li, Chloe, et autres
Publié: (2026)

Steering Evaluation-Aware Language Models to Act Like They Are Deployed
par: Hua, Tim Tian, et autres
Publié: (2025)

Quantum-Audit: Evaluating the Reasoning Limits of LLMs on Quantum Computing
par: Afane, Mohamed, et autres
Publié: (2026)

Auditing Rust Crates Effectively
par: Zoghbi, Lydia, et autres
Publié: (2026)

BengaliMoralBench: A Benchmark for Auditing Moral Reasoning in Large Language Models within Bengali Language and Culture
par: Ridoy, Shahriyar Zaman, et autres
Publié: (2025)

Statistical Hypothesis Testing for Auditing Robustness in Language Models
par: Rauba, Paulius, et autres
Publié: (2025)

Keeping Up with the Language Models: Systematic Benchmark Extension for Bias Auditing
par: Baldini, Ioana, et autres
Publié: (2023)

Robustly Improving LLM Fairness in Realistic Settings via Interpretability
par: Karvonen, Adam, et autres
Publié: (2025)

Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
par: Chen, Chaoran, et autres
Publié: (2026)

Stage-Audit: Auditable Source-Frontier Discovery for Cross-Wiki Tables
par: Shen, Chen
Publié: (2026)

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks
par: Karvonen, Adam, et autres
Publié: (2024)

Auditing Agent Harness Safety
par: Liu, Chengzhi, et autres
Publié: (2026)

Smart Audit System Empowered by LLM
par: Yao, Xu, et autres
Publié: (2024)

Direction-Flipped Influence Audits Reveal Hidden Structure in Moral Choices of LLMs
par: Blandfort, Phil, et autres
Publié: (2026)

Auditing the Use of Language Models to Guide Hiring Decisions
par: Gaebler, Johann D., et autres
Publié: (2024)

Auditing Prompt Caching in Language Model APIs
par: Gu, Chenchen, et autres
Publié: (2025)

Distilling Bayesian Belief States into Language Models for Auditable Negotiation
par: Cui, Zongqi, et autres
Publié: (2026)

Automated Benchmark Auditing for AI Agents and Large Language Models
par: Wang, Junlin, et autres
Publié: (2026)

CALM: Curiosity-Driven Auditing for Large Language Models
par: Zheng, Xiang, et autres
Publié: (2025)