REVIEW 3 cited by
Large Language Models are Strong Zero-Shot Retriever
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
In this work, we propose a simple method that applies a large language model (LLM) to large-scale retrieval in zero-shot scenarios. Our method, the Language language model as Retriever (LameR), is built upon no other neural models but an LLM, while breaking brute-force combinations of retrievers with LLMs and lifting the performance of zero-shot retrieval to be very competitive on benchmark datasets. Essentially, we propose to augment a query with its potential answers by prompting LLMs with a composition of the query and the query's in-domain candidates. The candidates, regardless of correct or wrong, are obtained by a vanilla retrieval procedure on the target collection. As a part of the prompts, they are likely to help LLM generate more precise answers by pattern imitation or candidate summarization. Even if all the candidates are wrong, the prompts at least make LLM aware of in-collection patterns and genres. Moreover, due to the low performance of a self-supervised retriever, the LLM-based query augmentation becomes less effective as the retriever bottlenecks the whole pipeline. Therefore, we propose to leverage a non-parametric lexicon-based method (e.g., BM25) as the retrieval module to capture query-document overlap in a literal fashion. As such, LameR makes the retrieval procedure transparent to the LLM, thus circumventing the performance bottleneck.
Forward citations
Cited by 3 Pith papers
-
Semantically Similar, Logically Distinct: Diagnosing the Semantic-Answerability Gap in Table RAG
On a new sibling-table benchmark, dense retrievers find the right table group but identify the uniquely answerable table at near-chance rates; cross-encoder reranking lifts top-1 from 18.2% to 57.4%.
-
A Tale of LLMs and Induced Small Proxies: Scalable Small Language Models for Knowledge Mining
LLM-written pipelines and LLM-generated labels are distilled into one small instruction-following model that performs classification and span extraction cheaply at corpus scale.
-
Harnessing the Power of Reinforcement Learning for Language-Model-Based Information Retriever via Query-Document Co-Augmentation
A bidirectional RL framework jointly optimizes LLM query and document augmentation and improves retrieval accuracy on BEIR benchmarks beyond query-only rewriting.
Discussion (0). Sign in to comment.