Image de couverture de livre

Towards Reliable Evaluation of Behavior Steering Interventions in LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pres, Itamar, Ruis, Laura, Lubana, Ekdeep Singh, Krueger, David
Format:	Preprint
Publié:	2024
Sujets:	Artificial Intelligence 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

How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations
par: Jaipersaud, Brandon, et autres
Publié: (2025)

Competition Dynamics Shape Algorithmic Phases of In-Context Learning
par: Park, Core Francisco, et autres
Publié: (2024)

Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics
par: Zur, Amir, et autres
Publié: (2025)

Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
par: Bigelow, Eric, et autres
Publié: (2025)

From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
par: Mueller, Aaron, et autres
Publié: (2025)

A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
par: Lee, Andrew, et autres
Publié: (2024)

In-Context Learning Dynamics with Random Binary Sequences
par: Bigelow, Eric J., et autres
Publié: (2023)

Emergence of Hierarchical Emotion Organization in Large Language Models
par: Zhao, Bo, et autres
Publié: (2025)

Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness
par: Banayeeanzade, Amin, et autres
Publié: (2025)

ICLR: In-Context Learning of Representations
par: Park, Core Francisco, et autres
Publié: (2024)

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
par: Bigelow, Eric, et autres
Publié: (2026)

Steering Towards Fairness: Mitigating Political Bias in LLMs
par: Nadeem, Afrozah, et autres
Publié: (2025)

The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning
par: Xu, Yi, et autres
Publié: (2026)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
par: Siu, Vincent, et autres
Publié: (2025)

LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs
par: Guo, Pei-Fu, et autres
Publié: (2025)

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders
par: Bohacek, Matyas, et autres
Publié: (2025)

Bias Beyond Borders: Political Ideology Evaluation and Steering in Multilingual LLMs
par: Nadeem, Afrozah, et autres
Publié: (2026)

On Robustness and Reliability of Benchmark-Based Evaluation of LLMs
par: Lunardi, Riccardo, et autres
Publié: (2025)

Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs
par: Cook, Jonathan, et autres
Publié: (2025)

Investigating Non-Transitivity in LLM-as-a-Judge
par: Xu, Yi, et autres
Publié: (2025)

CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models
par: Wang, Xintong, et autres
Publié: (2024)

Debating with More Persuasive LLMs Leads to More Truthful Answers
par: Khan, Akbir, et autres
Publié: (2024)

Steering Language Models Before They Speak: Logit-Level Interventions
par: An, Hyeseon, et autres
Publié: (2026)

How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs?
par: Doostmohammadi, Ehsan, et autres
Publié: (2024)

Can LLMs Evaluate What They Cannot Annotate? Revisiting LLM Reliability in Hate Speech Detection
par: Piot, Paloma, et autres
Publié: (2025)

KV Cache Steering for Controlling Frozen LLMs
par: Belitsky, Max, et autres
Publié: (2025)

Can LLMs replace Neil deGrasse Tyson? Evaluating the Reliability of LLMs as Science Communicators
par: Bajpai, Prasoon, et autres
Publié: (2024)

XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs
par: Chen, Zichen, et autres
Publié: (2023)

Towards Reliable Machine Translation: Scaling LLMs for Critical Error Detection and Safety
par: Chopra, Muskaan, et autres
Publié: (2026)

Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence
par: Lu, Yuyin, et autres
Publié: (2026)

AgentCompass: Towards Reliable Evaluation of Agentic Workflows in Production
par: Kartik, NVJK, et autres
Publié: (2025)

Steering Awareness: Detecting Activation Steering from Within
par: Rivera, Joshua Fonseca, et autres
Publié: (2025)

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
par: Kang, Diancheng, et autres
Publié: (2026)

Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games
par: Yadav, Neemesh, et autres
Publié: (2025)

Leveraging Implicit Sentiments: Enhancing Reliability and Validity in Psychological Trait Evaluation of LLMs
par: Ma, Huanhuan, et autres
Publié: (2025)

Exploring the Personality Traits of LLMs through Latent Features Steering
par: Yang, Shu, et autres
Publié: (2024)

Probing and Steering Evaluation Awareness of Language Models
par: Nguyen, Jord, et autres
Publié: (2025)

Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks
par: Chen, Kexin, et autres
Publié: (2024)

Steering LLMs for Formal Theorem Proving
par: Kirtania, Shashank, et autres
Publié: (2025)

Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations
par: Zhu, Jian-Qiao, et autres
Publié: (2025)