IREA: Intermediate Representation-based Embedding Alignment for Normative RAG
cs.CL
Submitted: 2026-10-04
Updated: 2026-10-04
Terminology
Sources
- GPT-4 Technical Report
- Constitutional AI: Harmlessness from AI Feedback
- LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
- SaGE: Evaluating Moral Consistency in Large Language Models
- AITA Generating Moral Judgements of the Crowd with Reasoning
- Enhancing Content Moderation with Culturally-Aware Models
- Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints
- Safe RLHF: Safe Reinforcement Learning from Human Feedback
- Towards Measuring the Representation of Subjective Global Opinions in Language Models
- Precise Zero-Shot Dense Retrieval without Relevance Labels
- Retrieval-Augmented Generation for Large Language Models: A Survey
- TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law
- Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
- Unsupervised Dense Information Retrieval with Contrastive Learning
- Are LLMs complicated ethical dilemma analyzers?
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- CulturePark: Boosting Cross-cultural Understanding in Large Language Models
- Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes
- Query Rewriting for Retrieval-Augmented Large Language Models
- Large Language Models: A Survey
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering