Iterative Critique-Refine Framework for Enhancing LLM Personalization
cs.CL, cs.AI, cs.IR
Submitted: 2025-10-28
Updated: 2026-10-11
Comments: Accepted to AACL 2026 (Main Conference)
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Personalized Graph-Based Retrieval for Large Language Models
- From Persona to Personalization: A Survey on Role-Playing Language Agents
- A Survey on Large Language Models for Personalized and Explainable Recommendations
- Large Language Models for User Interest Journeys
- LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
- Towards Measuring the Representation of Subjective Global Opinions in Language Models
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders
- Unsupervised Dense Information Retrieval with Contrastive Learning
- Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
- LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
- Few-shot Personalization of LLMs with Mis-aligned Responses
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Teach LLMs to Personalize -- An Approach inspired by Writing Education
- Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases
- A Preliminary Study of ChatGPT on News Recommendation: Personalization, Provider Fairness, Fake News
- Large Language Model-based Role-Playing for Personalized Medical Jargon Extraction
- Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache
- Lost in the Middle: How Language Models Use Long Contexts
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