Pith. sign in

REVIEW 5 cited by

Large Language Models are Zero-Shot Rankers for Recommender Systems

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

arxiv 2305.08845 v2 pith:UNJTMPXC submitted 2023-05-15 cs.IR cs.CL

Large Language Models are Zero-Shot Rankers for Recommender Systems

classification cs.IR cs.CL
keywords llmsrankingmodelsrecommendationzero-shotabilitiescandidatecandidates
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recently, large language models (LLMs) (e.g., GPT-4) have demonstrated impressive general-purpose task-solving abilities, including the potential to approach recommendation tasks. Along this line of research, this work aims to investigate the capacity of LLMs that act as the ranking model for recommender systems. We first formalize the recommendation problem as a conditional ranking task, considering sequential interaction histories as conditions and the items retrieved by other candidate generation models as candidates. To solve the ranking task by LLMs, we carefully design the prompting template and conduct extensive experiments on two widely-used datasets. We show that LLMs have promising zero-shot ranking abilities but (1) struggle to perceive the order of historical interactions, and (2) can be biased by popularity or item positions in the prompts. We demonstrate that these issues can be alleviated using specially designed prompting and bootstrapping strategies. Equipped with these insights, zero-shot LLMs can even challenge conventional recommendation models when ranking candidates are retrieved by multiple candidate generators. The code and processed datasets are available at https://github.com/RUCAIBox/LLMRank.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. One Pass, Any Order: Position-Invariant Listwise Reranking for LLM-Based Recommendation

    cs.IR 2026-04 conditional novelty 7.0

    InvariRank achieves permutation-invariant listwise reranking for LLM-based recommendations via a structured attention mask that blocks cross-candidate interactions and shared positional framing under RoPE, enabling st...

  2. Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations

    cs.LG 2024-02 unverdicted novelty 7.0

    HSTU-based generative recommenders with 1.5 trillion parameters scale as a power law with compute up to GPT-3 scale, outperform baselines by up to 65.8% NDCG, run 5-15x faster than FlashAttention2 on long sequences, a...

  3. LRanker: LLM Ranker for Massive Candidates

    cs.IR 2026-05 unverdicted novelty 5.0

    LRanker combines K-means candidate aggregation with graph-partitioned ensemble of query embeddings to improve LLM ranking accuracy and scalability on massive candidate pools, reporting 3-30% gains on RBench tasks up t...

  4. Ocean4Rec: Offline LLM-Derived OCEAN Profiles for Request-Time VOD Reranking

    cs.IR 2026-05 unverdicted novelty 5.0

    Ocean4Rec uses offline LLM to create OCEAN profiles for items and time-decayed user profiles for request-time numeric reranking, improving NDCG@20 by 7.6% and 61.5% over base+recency in offline VOD evaluations.

  5. Pre-trained LLMs Meet Sequential Recommenders: Efficient User-Centric Knowledge Distillation

    cs.IR 2026-04 unverdicted novelty 4.0

    A distillation technique embeds LLM-generated textual user profiles into efficient sequential recommenders without runtime LLM inference, architectural changes, or fine-tuning.