Image de couverture de livre

Theoretical Limits of Language Model Alignment

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Paes, Lucas Monteiro, Mackraz, Natalie, Theobald, Barry-John, Danieli, Federico
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Computation and Language Computers and Society Information Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Aligning LLMs by Predicting Preferences from User Writing Samples
par: Aroca-Ouellette, Stéphane, et autres
Publié: (2025)

DSO: Direct Steering Optimization for Bias Mitigation
par: Paes, Lucas Monteiro, et autres
Publié: (2025)

Bias after Prompting: Persistent Discrimination in Large Language Models
par: Sivakumar, Nivedha, et autres
Publié: (2025)

Multi-Group Fairness Evaluation via Conditional Value-at-Risk Testing
par: Paes, Lucas Monteiro, et autres
Publié: (2023)

Evaluating Gender Bias Transfer between Pre-trained and Prompt-Adapted Language Models
par: Mackraz, Natalie, et autres
Publié: (2024)

Selective Explanations
par: Paes, Lucas Monteiro, et autres
Publié: (2024)

Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models
par: Nagle, Alliot, et autres
Publié: (2024)

Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions
par: Wang, Hao, et autres
Publié: (2023)

Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits
par: Khisti, Ashish, et autres
Publié: (2024)

Scalable Identification and Prioritization of Requisition-Specific Personal Competencies Using Large Language Models
par: Li, Wanxin, et autres
Publié: (2026)

Algorithmic Arbitrariness in Content Moderation
par: Gomez, Juan Felipe, et autres
Publié: (2024)

Theoretical guarantees on the best-of-n alignment policy
par: Beirami, Ahmad, et autres
Publié: (2024)

Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs
par: Wang, Yinong Oliver, et autres
Publié: (2025)

Information-Theoretic Generative Clustering of Documents
par: Du, Xin, et autres
Publié: (2024)

Latent Space Alignment for Semantic Channel Equalization
par: Hüttebräucker, Tomás, et autres
Publié: (2024)

Evaluating the Performance of Large Language Models in Scientific Claim Detection and Classification
par: Faruk, Tanjim Bin
Publié: (2024)

Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Models
par: Vishwamitra, Nishant, et autres
Publié: (2023)

Limits to Predicting Online Speech Using Large Language Models
par: Remeli, Mina, et autres
Publié: (2024)

Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models
par: Sundar, Anirudh, et autres
Publié: (2025)

An Enhanced Text Compression Approach Using Transformer-based Language Models
par: Rahman, Chowdhury Mofizur, et autres
Publié: (2024)

Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Models
par: Guo, Keyan, et autres
Publié: (2024)

Skip-It? Theoretical Conditions for Layer Skipping in Vision-Language Models
par: Hartman, Max, et autres
Publié: (2025)

Epistemic Diversity and Knowledge Collapse in Large Language Models
par: Wright, Dustin, et autres
Publié: (2025)

Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions
par: Masoud, Reem I., et autres
Publié: (2023)

HeavyWater and SimplexWater: Distortion-Free LLM Watermarks for Low-Entropy Next-Token Predictions
par: Tsur, Dor, et autres
Publié: (2025)

On the Theoretical Limitations of Embedding-Based Retrieval
par: Weller, Orion, et autres
Publié: (2025)

Quantifying Logical Consistency in Transformers via Query-Key Alignment
par: Tulchinskii, Eduard, et autres
Publié: (2025)

Know Your Limits: Entropy Estimation Modeling for Compression and Generalization
par: Badger, Benjamin L., et autres
Publié: (2025)

Evidence Is All You Need: Ordering Imaging Studies via Language Model Alignment with the ACR Appropriateness Criteria
par: Yao, Michael S., et autres
Publié: (2024)

Breaking Language Barriers with MMTweets: Advancing Cross-Lingual Debunked Narrative Retrieval for Fact-Checking
par: Singh, Iknoor, et autres
Publié: (2023)

An Information Theoretic Perspective on Agentic System Design
par: He, Shizhe, et autres
Publié: (2025)

Analysing the Public Discourse around OpenAI's Text-To-Video Model 'Sora' using Topic Modeling
par: Parikh, Vatsal Vinay
Publié: (2024)

A Mathematical Theory for Learning Semantic Languages by Abstract Learners
par: Liao, Kuo-Yu, et autres
Publié: (2024)

Deliberative Alignment: Reasoning Enables Safer Language Models
par: Guan, Melody Y., et autres
Publié: (2024)

An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding
par: Hu, Dou, et autres
Publié: (2025)

SyllabusQA: A Course Logistics Question Answering Dataset
par: Fernandez, Nigel, et autres
Publié: (2024)

Navigating the Peril of Generated Alternative Facts: A ChatGPT-4 Fabricated Omega Variant Case as a Cautionary Tale in Medical Misinformation
par: Sallam, Malik, et autres
Publié: (2024)

Language Modeling Is Compression
par: Delétang, Grégoire, et autres
Publié: (2023)

Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition
par: Hamman, Faisal, et autres
Publié: (2023)

A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition
par: Hamman, Faisal, et autres
Publié: (2024)