Code, datasets, and checkpoints for the paper "Improving Passage Retrieval with Zero-Shot Question Generation (EMNLP 2022)" (⭐ 100)
As a critical task for large-scale commercial recommender systems, reranking has shown the potential of improving recommendation results by uncovering mutual influence among items. Reranking rearranges items in the initial ranking lists from the prev...
Reranking is a critical component in recommender systems, playing an essential role in refining the output of recommendation algorithms. Traditional reranking models have focused predominantly on accuracy, but modern applications demand consideration...
In passage retrieval system, the initial passage retrieval results may be unsatisfactory, which can be refined by a reranking scheme. Existing solutions to passage reranking focus on enriching the interaction between query and each passage separately...
Given I have yet to see a single re-ranking of the NHL coaches’ handsomeness, I figured I’d do it myself. Contrary to what some of the descriptors might imply, I am a straight man, and I have put ...
Points: 6 | Comments: 0 | Author: daoudc
[ICCV 2021] Instance-level Image Retrieval using Reranking Transformers (⭐ 146)
Large Language Models (LLMs) have transformed listwise document reranking by enabling global reasoning over candidate sets, yet single models often struggle to balance fine-grained relevance scoring with holistic cross-document analysis. We propose \...
In this work, we present a systematic and comprehensive empirical evaluation of state-of-the-art reranking methods, encompassing large language model (LLM)-based, lightweight contextual, and zero-shot approaches, with respect to their performance in...
Sampling diverse programs from a code language model and reranking with model likelihood is a popular method for code generation but it is prone to preferring degenerate solutions. Inspired by collaborative programming, we propose Coder-Reviewer rera...
Recent advancements in information retrieval have highlighted the potential of integrating visual and textual information, yet effective reranking for image-text documents remains challenging due to the modality gap and scarcity of aligned datasets....
Reranking, the process of refining the output of a first-stage retriever, is often considered computationally expensive, especially with Large Language Models. Borrowing from recent advances in document compression for RAG, we reduce the input size b...
This paper introduces an improved reranking method for the Bag-of-Words (BoW) based image search. Built on [1], a directed image graph robust to outlier distraction is proposed. In our approach, the relevance among images is encoded in the image grap...
Standard decoding approaches for conditional text generation tasks typically search for an output hypothesis with high model probability, but this may not yield the best hypothesis according to human judgments of quality. Reranking to optimize for "d...
Points: 5 | Comments: 3 | Author: matusa
Points: 8 | Comments: 4 | Author: karenishe
Most conventional Retrieval-Augmented Generation (RAG) pipelines rely on relevance-based retrieval, which often misaligns with utility -- that is, whether the retrieved passages actually improve the quality of the generated text specific to a downstr...
A Vector Store written in Go - Supports hybrid retrieval over BM25, Flat, HNSW, IVF, PQ and IVFPQ Index with Quantization, Metadata Filtering, Reranking, Reciprocal Rank Fusion, Soft Deletes, Index Rebuilds and much much more (⭐ 106)
All-in-One: Text Embedding, Retrieval, Reranking and RAG in Transformers (⭐ 74)
to 7th in the prize money rankings will be given priority for the first half of next year's Tour (until the first reranking). This year, No. 4 Rikuya