REVIEW 6 cited by
RosePO: Aligning LLM-based Recommenders with Human Values
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recently, there has been a growing interest in leveraging Large Language Models (LLMs) for recommendation systems, which usually adapt a pre-trained LLM to the recommendation scenario through supervised fine-tuning (SFT). However, both the pre-training and SFT stages fail to explicitly model the comparative relationships of a user's preferences on different items. To construct a "helpful and harmless" LLM-based recommender, we propose a general framework -- Recommendation with smoothing personalized Preference Optimization (RosePO), which better aligns with customized human values during the post-training stage. Specifically, in addition to the input and chosen response that naturally align with SFT data, we design a rejected sampling strategy tailored for enhancing helpfulness, along with two strategies aimed at mitigating biases to promote harmlessness. To ensure robustness against uncertain labels present in automatically constructed preference data, we introduce a personalized smoothing factor predicted by a preference oracle into the optimization objective. Evaluation on three real-world datasets demonstrates the effectiveness of our method, showcasing not only improved recommendation performance but also mitigation of semantic hallucination and popularity bias.
Forward citations
Cited by 6 Pith papers
-
BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models
BEAR is a cheap token-level top-B regularizer for LLM-based recommendation, but its central claim that this condition is necessary for beam-search survival is incorrect.
-
LBR: Towards Mitigating Length Bias in Large Language Models for Recommendation
LBR removes length bias in LLM recommenders via length-aware attention offsets and Trie-branching information-length normalization, improving accuracy and fairness with negligible cost.
-
Uncertainty-aware Generative Recommendation
UGR injects uncertainty into generative recommendation preference optimization via confidence-weighted rewards, difficulty-aware reweighting, and explicit confidence tokens, improving ranking accuracy and training stability.
-
Architecture is All You Need: Improving LLM Recommenders by Dropping the Text
A 2.2M-parameter Llama-style model using only item IDs beats a 7B-parameter text-based LLM recommender and SASRec on MovieLens-10M.
-
BiFair: A Fairness-aware Training Framework for LLM-enhanced Recommender Systems via Bi-level Optimization
BiFair uses bi-level optimization to refine LLM-generated item embeddings and recommender projector weights together, with an entropy-based group balancing loss, and reports improved item-group fairness on three Amazo...
-
GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models
A survey of LLM-based generative recommendation systems, covering application settings, training pipelines, industrial deployment challenges, and future directions.
Discussion (0). Continue with ORCID to comment.