paper-with-me

Papers

Large Language Models are Not Stable Recommender Systems

2023-12-25 · TianHui Ma, Yuan Cheng, HengShu Zhu, Hui Xiong

With the significant successes of large language models (LLMs) in many natural language processing tasks, there is growing interest among researchers in exploring LLMs for novel recommender systems. However, we have observed that directly using LLMs as a recommender system is usually unstable due to its inherent position bias. To this end, we introduce exploratory research and find consistent patterns of positional bias in LLMs that influence the performance of recommendation across a range of scenarios. Then, we propose a Bayesian probabilistic framework, STELLA (Stable LLM for Recommendation), which involves a two-stage pipeline. During the first probing stage, we identify patterns in a transition matrix using a probing detection dataset. And in the second recommendation stage, a Bayesian strategy is employed to adjust the biased output of LLMs with an entropy indicator. Therefore, our framework can capitalize on existing pattern information to calibrate instability of LLMs, and enhance recommendation performance. Finally, extensive experiments clearly validate the effectiveness of our framework.

📄 PDF Abstract BibTeX arXiv:2312.15746

Code (0)

등록된 구현이 없습니다.

Tasks

Recommendation Systems

Similar Papers 제목 키워드 기반

A Survey on LLM-based News Recommender Systems

2025-02-13 · Rongyao Wang, Veronica Liesaputra, Zhiyi Huang

News recommender systems play a critical role in mitigating the information overload problem. In recent years, due to the successful applications of large language model technologies, researchers have utilized Discrimina…

BenchmarkingFairnessLanguage ModelingLanguage Modelling+4

Parallel and Mini-Batch Stable Matching for Large-Scale Reciprocal Recommender Systems

2024-11-28 · Kento Nakada, Kazuki Kawamura, Ryosuke Furukawa

Reciprocal recommender systems (RRSs) are crucial in online two-sided matching platforms, such as online job or dating markets, as they need to consider the preferences of both sides of the match. The concentration of re…

Recommendation Systems

RecAI: Leveraging Large Language Models for Next-Generation Recommender Systems

2024-03-11 · Jianxun Lian, Yuxuan Lei, Xu Huang, Jing Yao 외

This paper introduces RecAI, a practical toolkit designed to augment or even revolutionize recommender systems with the advanced capabilities of Large Language Models (LLMs). RecAI provides a suite of tools, including Re…

AI AgentRecommendation Systems

Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond

2024-10-10 · Qi Wang, Jindong Li, Shiqi Wang, Qianli Xing 외

Large language models (LLMs) have not only revolutionized the field of natural language processing (NLP) but also have the potential to bring a paradigm shift in many other fields due to their remarkable abilities of lan…

Large Language ModelRecommendation Systems

Large Language Models Make Sample-Efficient Recommender Systems

2024-06-04 · Jianghao Lin, Xinyi Dai, Rong Shan, Bo Chen 외

Large language models (LLMs) have achieved remarkable progress in the field of natural language processing (NLP), demonstrating remarkable abilities in producing text that resembles human language for various tasks. This…

Recommendation Systems