Pith. sign in

REVIEW 3 cited by

PaRaDe: Passage Ranking using Demonstrations with Large Language Models

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 2310.14408 v1 pith:Z4CA2ODX submitted 2023-10-22 cs.IR

classification cs.IR
keywords demonstrationspassagerankingdemonstrationgenerationhelpfulimprovelanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent studies show that large language models (LLMs) can be instructed to effectively perform zero-shot passage re-ranking, in which the results of a first stage retrieval method, such as BM25, are rated and reordered to improve relevance. In this work, we improve LLM-based re-ranking by algorithmically selecting few-shot demonstrations to include in the prompt. Our analysis investigates the conditions where demonstrations are most helpful, and shows that adding even one demonstration is significantly beneficial. We propose a novel demonstration selection strategy based on difficulty rather than the commonly used semantic similarity. Furthermore, we find that demonstrations helpful for ranking are also effective at question generation. We hope our work will spur more principled research into question generation and passage ranking.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matching

    cs.CL 2025-06 conditional novelty 6.0 of 10

    CLG selects many-shot demonstrations by matching fine-tuning gradients of a small language model to the full training set, improving accuracy over random selection by 2-4%.

  2. Evaluating and Improving Graph to Text Generation with Large Language Models

    cs.CL 2025-01 conditional novelty 6.0 of 10

    Introducing PlanGTG, a 29k-pair instruction dataset with reordering and attribution subtasks, and fine-tuning 7B LLMs on it improves graph-to-text generation on WebNLG and DART over untuned and dataset-tuned baselines.

  3. PaSa: An LLM Agent for Comprehensive Academic Paper Search

    cs.IR 2025-01 conditional novelty 6.0 of 10

    PaSa, a two-agent LLM system trained with session-level RL, reports substantially higher recall than existing academic search baselines on complex paper-finding queries.

Pith tools