Pith. sign in

REVIEW 21 cited by

Multi-Stage Document Ranking with BERT

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 1910.14424 v1 pith:S4SNQQXT submitted 2019-10-31 cs.IR cs.LG

Multi-Stage Document Ranking with BERT

classification cs.IR cs.LG
keywords rankingbertdocumentlanguagelatencymodelmulti-stagequality
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The advent of deep neural networks pre-trained via language modeling tasks has spurred a number of successful applications in natural language processing. This work explores one such popular model, BERT, in the context of document ranking. We propose two variants, called monoBERT and duoBERT, that formulate the ranking problem as pointwise and pairwise classification, respectively. These two models are arranged in a multi-stage ranking architecture to form an end-to-end search system. One major advantage of this design is the ability to trade off quality against latency by controlling the admission of candidates into each pipeline stage, and by doing so, we are able to find operating points that offer a good balance between these two competing metrics. On two large-scale datasets, MS MARCO and TREC CAR, experiments show that our model produces results that are either at or comparable to the state of the art. Ablation studies show the contributions of each component and characterize the latency/quality tradeoff space.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 21 Pith papers

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

  1. A Sensitivity-Aware Test Collection for Search Among Personal Information

    cs.IR 2026-06 accept novelty 7.0

    A new sensitivity-labeled test collection is released from Enron emails with crowdsourced queries, relevance judgments, and LLM extensions for evaluating sensitivity-aware search.

  2. The Voronoi Bottleneck: Capacity-Aware Dense Retrieval for Product Search

    cs.IR 2026-06 unverdicted novelty 7.0

    Proves Voronoi complexity equals sign-rank for top-1 retrieval, introduces CUS diagnostic predicting retrieval failure at AUC >0.8 without labels, and AT-DW-InfoNCE objective with derived alpha^*=2.0 that improves Rec...

  3. Argus-Retriever: Vision-LLM Late-Interaction Retrieval with Region-Aware Query-Conditioned MoE for Visual Document Retrieval

    cs.IR 2026-06 unverdicted novelty 7.0

    Argus achieves the highest reported NDCG scores among open late-interaction models on ViDoRe V1 and combined V1+V2 by introducing query-dependent document representations via a region-aware MoE on Qwen3.5-VL, trained ...

  4. ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression

    cs.IR 2026-04 conditional novelty 7.0

    ResRank unifies retrieval and listwise reranking by compressing passages to one token each, using residual connections and cosine-similarity scoring, achieving competitive effectiveness on TREC DL and BEIR benchmarks ...

  5. Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrieval

    cs.IR 2026-04 unverdicted novelty 7.0

    BAGEL is a Bayesian active learning framework that uses Gaussian Processes to propagate LLM relevance signals across embedding space and guide global exploration, outperforming standard LLM reranking under identical b...

  6. M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation

    cs.CL 2024-02 unverdicted novelty 7.0

    M3-Embedding is a single model for multi-lingual, multi-functional, and multi-granular text embeddings trained via self-knowledge distillation that achieves new state-of-the-art results on multilingual, cross-lingual,...

  7. Structure-aware Relative Policy Optimization for Ranking

    cs.IR 2026-07 conditional novelty 6.0

    Dividing pairwise reward differences by top-weighted Kendall-tau distance in group-relative policy optimization improves listwise ranking performance.

  8. SynH-Rank: Quality-Aware Code Search via Diverse Data Synthesis and Hierarchical Ranking Training

    cs.SE 2026-07 conditional novelty 6.0

    A quality-aware code-search reranking framework with LLM-synthesized quality variants and a hierarchical ranking loss beats relevance-only training on a new QPA/MCA benchmark.

  9. Every Sample Counts: Supervised Fine-Tuning of Language Models with Pointwise Constraints

    eess.SP 2026-07 conditional novelty 6.0

    Pointwise constrained fine-tuning via sample-wise augmented Lagrangians and learned relaxations reduces tail constraint violations across safety, tool-calling, and re-ranking while preserving average task performance.

  10. MIRA: An LLM-Assisted Benchmark for Multi-Category Integrated Retrieval

    cs.IR 2026-05 unverdicted novelty 6.0

    MIRA is a new benchmark for multi-category integrated retrieval built from real queries on a social science platform, with LLM assistance for topic descriptions and relevance labeling across four item categories.

  11. Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models

    cs.IR 2026-04 conditional novelty 6.0

    RouteHead trains a lightweight router to dynamically select optimal LLM attention heads per query for improved attention-based document re-ranking.

  12. Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning

    cs.CL 2026-04 conditional novelty 6.0

    RRPO formulates document reranking as a sequential MDP and optimizes a pointwise reranker with PPO using LLM generation rewards and a reference-anchored deterministic baseline.

  13. RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models

    cs.IR 2025-02 unverdicted novelty 6.0

    RankFlow deploys four LLM roles in sequence to rewrite queries, generate pseudo-answers, summarize passages, and rerank candidates, outperforming prior methods on TREC-DL, BEIR, and NovelEval.

  14. RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!

    cs.IR 2023-12 conditional novelty 6.0

    RankZephyr is a new open-source LLM that closes the effectiveness gap with GPT-4 for zero-shot listwise reranking while showing robustness to input ordering and document count.

  15. Text and Code Embeddings by Contrastive Pre-Training

    cs.CL 2022-01 unverdicted novelty 6.0

    Contrastive pre-training on unsupervised data at scale creates text and code embeddings that set new state-of-the-art results on classification and semantic search benchmarks.

  16. MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking

    cs.IR 2026-07 conditional novelty 4.0

    MagicSelector combines RL-trained task decomposition, iterative hard-negative reranking, and adaptive top-k truncation to improve mobile-agent tool retrieval, evaluated on a new MTDTool benchmark.

  17. InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost

    cs.CL 2026-07 conditional novelty 4.0

    A 4B-model cascade for Thai KOL matching reaches 94.1% P@5 on 11 queries, matching a frontier model, with pairwise SimPO training transferring end-to-end while pointwise SFT+GRPO does not.

  18. SPARK: Search Personalization via Agent-Driven Retrieval and Knowledge-sharing

    cs.AI 2025-12 conditional novelty 4.0

    SPARK is a proposed framework that coordinates persona-based LLM agents with layered memory and three collaboration protocols to produce personalized search.

  19. Query pipeline optimization for cancer patient question answering systems

    cs.CL 2024-12 unverdicted novelty 4.0

    Three-aspect RAG query pipeline optimization for cancer patient QA introduces HSRDR and SEOS and reports 5.24% accuracy gain on Claude-3-haiku versus chain-of-thought on a custom dataset.

  20. Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrieval

    cs.IR 2026-04 conditional novelty 3.0

    Reproducibility study confirms Hypencoder's non-linear query-specific scoring improves retrieval over bi-encoders on standard benchmarks but standard methods remain faster and hard-task results are mixed due to implem...

  21. A Survey on Retrieval-Augmented Text Generation for Large Language Models

    cs.IR 2024-04 unverdicted novelty 2.0

    A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.