paper-with-me

Papers

How Does BERT Rerank Passages? An Attribution Analysis with Information Bottlenecks

2021-11-01 · EMNLP (BlackboxNLP) 2021 11 · Zhiying Jiang, Raphael Tang, Ji Xin, Jimmy Lin

Fine-tuned pre-trained transformers achieve the state of the art in passage reranking. Unfortunately, how they make their predictions remains vastly unexplained, especially at the end-to-end, input-to-output level. Little known is how tokens, layers, and passages precisely contribute to the final prediction. In this paper, we address this gap by leveraging the recently developed information bottlenecks for attribution (IBA) framework. On BERT-based models for passage reranking, we quantitatively demonstrate the framework’s veracity in extracting attribution maps, from which we perform detailed, token-wise analysis about how predictions are made. Overall, we find that BERT still cares about exact token matching for reranking; the [CLS] token mainly gathers information for predictions at the last layer; top-ranked passages are robust to token removal; and BERT fine-tuned on MSMARCO has positional bias towards the start of the passage.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Passage RerankingReranking

Similar Papers 제목 키워드 기반

Legal Domain Adaptation of Modern BERT Models

2026-06-26 · Dominik Stammbach, Peter Henderson arxiv

We investigate domain adaptation of modern BERT models in the legal domain. We further pre-train ModernBERT on all US court opinions using the masked language modeling objective. Although ModernBERT has been trained on r…

Domain Adaptation

Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering

2021-01-01 · Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen 외

Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer. In th…

Natural QuestionsOpen-Domain Question AnsweringPassage RerankingQuestion Answering+3

Rank-K: Test-Time Reasoning for Listwise Reranking

2025-05-20 · Eugene Yang, Andrew Yates, Kathryn Ricci, Orion Weller 외

Retrieve-and-rerank is a popular retrieval pipeline because of its ability to make slow but effective rerankers efficient enough at query time by reducing the number of comparisons. Recent works in neural rerankers take …

Language ModelingLanguage ModellingPassage RerankingReranking+1

CoRanking: Collaborative Ranking with Small and Large Ranking Agents

2025-03-30 · Wenhan Liu, Xinyu Ma, Yutao Zhu, Lixin Su 외

Large Language Models (LLMs) have demonstrated superior listwise ranking performance. However, their superior performance often relies on large-scale parameters (\eg, GPT-4) and a repetitive sliding window process, which…

Collaborative Ranking

HLTCOE at TREC 2023 NeuCLIR Track

2024-04-11 · Eugene Yang, Dawn Lawrie, James Mayfield

The HLTCOE team applied PLAID, an mT5 reranker, and document translation to the TREC 2023 NeuCLIR track. For PLAID we included a variety of models and training techniques -- the English model released with ColBERT v2, tr…

AllDocument Translation