Researchers have developed a new method for group recommender systems that uses fine-tuned Large Language Models (LLMs) to dynamically select the best recommendation strategy based on predicted human preferences for fairness, satisfaction, and consensus. By training LLMs on human survey data, they created "Judgmental Llama" and "Judgmental OLMo" models that simulate group assessments. A user study with 284 participants validated this approach, showing it achieved higher scores for satisfaction and group consensus, particularly when considering interaction effects between the LLM's judgments and group configurations. AI
IMPACT This research could lead to more personalized and fair recommendations by enabling systems to better understand and adapt to diverse user preferences within groups.
RANK_REASON The cluster contains two identical arXiv preprints detailing a research paper on LLM applications in recommender systems.
Read on arXiv cs.IR (Information Retrieval) →
- alphaXiv
- arXiv
- CatalyzeX
- Cedric Waterschoot
- CORE Recommender
- DagsHub
- DeepSeek-V3.1
- Gotit.pub
- Hugging Face
- Judgmental Llama
- Judgmental OLMo
- ScienceCast
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
