Image de couverture de livre

On the Limitations of Steering in Language Model Alignment

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Niranjan, Chebrolu, Jaidka, Kokil, Yeo, Gerard Christopher
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

From Passive to Persuasive: Localized Activation Injection for Empathy and Negotiation
par: Chebrolu, Niranjan, et autres
Publié: (2025)

Conversations: Love Them, Hate Them, Steer Them
par: Chebrolu, Niranjan, et autres
Publié: (2025)

Do You Trust Me? Cognitive-Affective Signatures of Trustworthiness in Large Language Models
par: Yeo, Gerard, et autres
Publié: (2025)

Beyond Context to Cognitive Appraisal: Emotion Reasoning as a Theory of Mind Benchmark for Large Language Models
par: Yeo, Gerard Christopher, et autres
Publié: (2025)

Incivility and Rigidity: Evaluating the Risks of Fine-Tuning LLMs for Political Argumentation
par: Churina, Svetlana, et autres
Publié: (2024)

Beyond Text: Leveraging Multi-Task Learning and Cognitive Appraisal Theory for Post-Purchase Intention Analysis
par: Yeo, Gerard Christopher, et autres
Publié: (2024)

Learning Through Dialogue: Engagement and Efficacy Matter More Than Explanations
par: Furniturewala, Shaz, et autres
Publié: (2026)

Layer of Truth: Probing Belief Shifts under Continual Pre-Training Poisoning
par: Churina, Svetlana, et autres
Publié: (2025)

Labels or Input? Rethinking Augmentation in Multimodal Hate Detection
par: Singh, Sahajpreet, et autres
Publié: (2025)

Impact of Decoding Methods on Human Alignment of Conversational LLMs
par: Furniturewala, Shaz, et autres
Publié: (2024)

Turn-Level Empathy Prediction Using Psychological Indicators
par: Furniturewala, Shaz, et autres
Publié: (2024)

The MediaSpin Dataset: Post-Publication News Headline Edits Annotated for Media Bias
par: Verma, Preetika, et autres
Publié: (2024)

CURATRON: Complete and Robust Preference Data for Rigorous Alignment of Large Language Models
par: Nguyen, Son The, et autres
Publié: (2024)

Reading Between the Lines: How Electronic Nonverbal Cues shape Emotion Decoding
par: Kumar, Taara, et autres
Publié: (2026)

Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods
par: Wolf, Yotam, et autres
Publié: (2024)

Fundamental Limitations of Alignment in Large Language Models
par: Wolf, Yotam, et autres
Publié: (2023)

Probing the Limits of Stylistic Alignment in Vision-Language Models
par: Farajidizaji, Asma, et autres
Publié: (2025)

Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
par: Banerjee, Somnath, et autres
Publié: (2025)

"Reasoning" with Rhetoric: On the Style-Evidence Tradeoff in LLM-Generated Counter-Arguments
par: Verma, Preetika, et autres
Publié: (2024)

Self-Steering Language Models
par: Grand, Gabriel, et autres
Publié: (2025)

CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models
par: Li, Mengfan, et autres
Publié: (2026)

Towards Inference-time Category-wise Safety Steering for Large Language Models
par: Bhattacharjee, Amrita, et autres
Publié: (2024)

Steering When Necessary: Flexible Steering Large Language Models with Backtracking
par: Cheng, Zifeng, et autres
Publié: (2025)

Hateful Meme Detection through Context-Sensitive Prompting and Fine-Grained Labeling
par: Ouyang, Rongxin, et autres
Publié: (2024)

PHAnToM: Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models
par: Tan, Fiona Anting, et autres
Publié: (2024)

Inference-time Alignment via Sparse Junction Steering
par: Hu, Runyi, et autres
Publié: (2026)

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

Activation Scaling for Steering and Interpreting Language Models
par: Stoehr, Niklas, et autres
Publié: (2024)

PlotTwist: A Creative Plot Generation Framework with Small Language Models
par: Thorat, Abhinav, et autres
Publié: (2026)

GitSearch: Enhancing Community Notes Generation with Gap-Informed Targeted Search
par: Singh, Sahajpreet, et autres
Publié: (2026)

Continual Learning with Global Alignment
par: Bai, Xueying, et autres
Publié: (2022)

Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations
par: Braun, Joschka
Publié: (2026)

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

Compositional Steering of Large Language Models with Steering Tokens
par: Radevski, Gorjan, et autres
Publié: (2026)

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
par: Li, Hao, et autres
Publié: (2026)

Prompt-Based Value Steering of Large Language Models
par: Abbo, Giulio Antonio, et autres
Publié: (2025)

Cross-Lingual Activation Steering for Multilingual Language Models
par: Pokharel, Rhitabrat, et autres
Publié: (2026)

Steering Large Language Models to Evaluate and Amplify Creativity
par: Olson, Matthew Lyle, et autres
Publié: (2024)

From What to Why: Thought-Space Recommendation with Small Language Models
par: Biswas, Prosenjit, et autres
Publié: (2025)

Natural Language Interaction with Databases on Edge Devices in the Internet of Battlefield Things
par: Molek, Christopher D., et autres
Publié: (2025)