Cover Image

VAL-Bench: Belief Consistency as a measure for Value Alignment in Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gupta, Aman, O'Shea, Denny, Barez, Fazl
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SafetyNet: Detecting Harmful Outputs in LLMs by Modeling and Monitoring Deceptive Behaviors
by: Chaudhary, Maheep, et al.
Published: (2025)

Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models
by: Lan, Michael, et al.
Published: (2023)

Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustness
by: Fu, Tingchen, et al.
Published: (2025)

PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
by: Fu, Tingchen, et al.
Published: (2024)

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
by: Oozeer, Narmeen, et al.
Published: (2025)

Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions
by: Neo, Clement, et al.
Published: (2024)

Rethinking AI Cultural Alignment
by: Bravansky, Michal, et al.
Published: (2025)

Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders
by: Lan, Michael, et al.
Published: (2024)

Scaling sparse feature circuit finding for in-context learning
by: Kharlapenko, Dmitrii, et al.
Published: (2025)

Query Circuits: Explaining How Language Models Answer User Prompts
by: Wu, Tung-Yu, et al.
Published: (2025)

Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
by: Simhi, Adi, et al.
Published: (2026)

MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
by: Saha, Partha Pratim, et al.
Published: (2026)

MedVAL: Toward Expert-Level Medical Text Validation with Language Models
by: Aali, Asad, et al.
Published: (2025)

On the Robustness of Reward Models for Language Model Alignment
by: Hong, Jiwoo, et al.
Published: (2025)

LocalValueBench: A Collaboratively Built and Extensible Benchmark for Evaluating Localized Value Alignment and Ethical Safety in Large Language Models
by: Meadows, Gwenyth Isobel, et al.
Published: (2024)

Large Language Models Relearn Removed Concepts
by: Lo, Michelle, et al.
Published: (2024)

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
by: Denison, Carson, et al.
Published: (2024)

Are Large Language Models Consistent over Value-laden Questions?
by: Moore, Jared, et al.
Published: (2024)

FairBelief -- Assessing Harmful Beliefs in Language Models
by: Setzu, Mattia, et al.
Published: (2024)

FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench (Automated Multi-shot Jailbreaks)
by: Priyanshu, Aman, et al.
Published: (2024)

Understanding Addition in Transformers
by: Quirke, Philip, et al.
Published: (2023)

Benchmarking Multi-National Value Alignment for Large Language Models
by: Shi, Weijie, et al.
Published: (2025)

Probing the Limits of Stylistic Alignment in Vision-Language Models
by: Farajidizaji, Asma, et al.
Published: (2025)

Are LLM Belief Updates Consistent with Bayes' Theorem?
by: Imran, Sohaib, et al.
Published: (2025)

VAL: Interactive Task Learning with GPT Dialog Parsing
by: Lawley, Lane, et al.
Published: (2023)

Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration
by: Mao, Xin, et al.
Published: (2024)

PoliticsBench: Benchmarking Political Values in Large Language Models with Multi-Turn Roleplay
by: Khetan, Rohan, et al.
Published: (2026)

Inference-Time Language Model Alignment via Integrated Value Guidance
by: Liu, Zhixuan, et al.
Published: (2024)

AlignBench: Benchmarking Chinese Alignment of Large Language Models
by: Liu, Xiao, et al.
Published: (2023)

EigenBench: A Comparative Behavioral Measure of Value Alignment
by: Chang, Jonathn, et al.
Published: (2025)

Semantic Consistency for Assuring Reliability of Large Language Models
by: Raj, Harsh, et al.
Published: (2023)

Diverse Human Value Alignment for Large Language Models via Ethical Reasoning
by: Wang, Jiahao, et al.
Published: (2025)

VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models
by: Kim, Woojin, et al.
Published: (2026)

Accumulating Context Changes the Beliefs of Language Models
by: Geng, Jiayi, et al.
Published: (2025)

Language Models Represent Beliefs of Self and Others
by: Zhu, Wentao, et al.
Published: (2024)

Value Augmented Sampling for Language Model Alignment and Personalization
by: Han, Seungwook, et al.
Published: (2024)

Premise Order Matters in Reasoning with Large Language Models
by: Chen, Xinyun, et al.
Published: (2024)

Do Language Models Think Consistently? A Study of Value Preferences Across Varying Response Lengths
by: Nair, Inderjeet, et al.
Published: (2025)

Internal Value Alignment in Large Language Models through Controlled Value Vector Activation
by: Jin, Haoran, et al.
Published: (2025)

Best-of-N Jailbreaking
by: Hughes, John, et al.
Published: (2024)