Cover Image

Normative Conflicts and Shallow AI Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Millière, Raphaël
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Philosophy of Cognitive Science in the Age of Deep Learning
by: Millière, Raphaël
Published: (2024)

Language Models as Models of Language
by: Millière, Raphaël
Published: (2024)

A Philosophical Introduction to Language Models - Part II: The Way Forward
by: Millière, Raphaël, et al.
Published: (2024)

Anthropocentric bias in language model evaluation
by: Millière, Raphaël, et al.
Published: (2024)

The Vector Grounding Problem
by: Mollo, Dimitri Coelho, et al.
Published: (2023)

A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates
by: Millière, Raphaël, et al.
Published: (2024)

How Do Transformers Learn Variable Binding in Symbolic Programs?
by: Wu, Yiwei, et al.
Published: (2025)

LLMs as Models for Analogical Reasoning
by: Musker, Sam, et al.
Published: (2024)

Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in Large Language Models
by: Yousefi, Safoora, et al.
Published: (2023)

Why Is RLHF Alignment Shallow? A Gradient Analysis
by: Young, Robin
Published: (2026)

Decoupled Proxy Alignment: Mitigating Language Prior Conflict for Multimodal Alignment in MLLM
by: Tan, Chenkun, et al.
Published: (2025)

Philosophy of cognitive science in the age of deep learning
by: Raphaël Millière
Published: (2024)

CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment
by: Li, Jiangnan, et al.
Published: (2025)

Reward-free Alignment for Conflicting Objectives
by: Chen, Peter, et al.
Published: (2026)

ConflictBench: Evaluating Human-AI Conflict via Interactive and Visually Grounded Environments
by: Zhao, Weixiang, et al.
Published: (2026)

Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM Alignment
by: Liu, Zixuan, et al.
Published: (2025)

AI Alignment Breaks at the Edge
by: Bao, Han, et al.
Published: (2026)

Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment
by: Li, Moxin, et al.
Published: (2025)

Deontological Keyword Bias: The Impact of Modal Expressions on Normative Judgments of Language Models
by: Park, Bumjin, et al.
Published: (2025)

Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models
by: Nair, Inderjeet, et al.
Published: (2026)

Beyond Shallow Heuristics: Leveraging Human Intuition for Curriculum Learning
by: Toborek, Vanessa, et al.
Published: (2025)

Consensus or Conflict? Fine-Grained Evaluation of Conflicting Answers in Question-Answering
by: Nachshoni, Eviatar, et al.
Published: (2025)

Evaluating Behavioral Alignment in Conflict Dialogue: A Multi-Dimensional Comparison of LLM Agents and Humans
by: Kwon, Deuksin, et al.
Published: (2025)

Value-Action Alignment in Large Language Models under Privacy-Prosocial Conflict
by: Chen, Guanyu, et al.
Published: (2026)

Challenges and Future Directions of Data-Centric AI Alignment
by: Yeh, Min-Hsuan, et al.
Published: (2024)

Shallow Cross-Encoders for Low-Latency Retrieval
by: Petrov, Aleksandr V., et al.
Published: (2024)

Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment
by: Wang, Kun, et al.
Published: (2026)

Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training
by: Wu, Yu-Hang, et al.
Published: (2026)

Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection
by: Chen, Tianxiang, et al.
Published: (2024)

Rehearsal: Simulating Conflict to Teach Conflict Resolution
by: Shaikh, Omar, et al.
Published: (2023)

Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
by: Wu, Addison J., et al.
Published: (2026)

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?
by: Qi, Xuan, et al.
Published: (2025)

The Reader is the Metric: How Textual Features and Reader Profiles Explain Conflicting Evaluations of AI Creative Writing
by: Marco, Guillermo, et al.
Published: (2025)

Where Norms and References Collide: Evaluating LLMs on Normative Reasoning
by: Abrams, Mitchell, et al.
Published: (2026)

Conflicts in Texts: Data, Implications and Challenges
by: Liu, Siyi, et al.
Published: (2025)

The Unintended Trade-off of AI Alignment:Balancing Hallucination Mitigation and Safety in LLMs
by: Mahmoud, Omar, et al.
Published: (2025)

Pluralism in AI Governance: Toward Sociotechnical Alignment and Normative Coherence
by: Nkongolo, Mike Wa
Published: (2026)

Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data
by: Xing, Yue, et al.
Published: (2024)

Great Memory, Shallow Reasoning: Limits of $k$NN-LMs
by: Geng, Shangyi, et al.
Published: (2024)

Position: Towards Bidirectional Human-AI Alignment
by: Shen, Hua, et al.
Published: (2024)