Signals 4 · free daily AI digest

Effective Dense Retrieval using Only In-Context Examples

Paper recorded by Signals 4 on 2026-09-29 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-29 on arXiv · recorded by Signals 4 on 2026-09-30

Category: cs.CL · 自然语言处理 · first seen 2026-09-30

Abstract

Turning decoder-only large language models (LLMs) into strong dense retrievers typically requires some form of retriever training. In this paper, we ask whether LLMs can instead be prompted to produce effective representations for dense retrieval given only a few in-context examples. To answer this, we introduce RICE (Representations from In-Context Examples), a simple "training-free" approach tha

Read on arXiv →

#7 most recent of 292 cs.CL papers we have recorded · ↑ newer: Pruning for Efficiency, Paying in Fairness: Demographic Disparities in · ↓ older: Dr. OPD: Learning What to Follow for Optimal On-Policy Distillation of
Cite this page: Effective Dense Retrieval using Only In-Context Examples: the #7 most recent of 292 cs.CL papers we have recorded (as of 2026-09-29). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/effective-dense-retrieval-using-only-in-context-examples.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions