mlsanityData to 7 Oct 2026

Efficient Title Reranker for Fast and Improved Knowledge-Intense NLP

arXiv 2312.12430 ↗First posted 19 Dec 2023cs.IR cs.AI cs.CLcited by 0

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

In recent RAG approaches, rerankers play a pivotal role in refining retrieval accuracy with the ability of revealing logical relations for each pair of query and text. However, existing rerankers are required to repeatedly encode the query and a large number of long retrieved text. This results in high computational costs and limits the number of retrieved text, hindering accuracy. As a remedy of the problem, we introduce the Efficient Title Reranker via Broadcasting Query Encoder, a novel technique for title reranking that achieves a 20x-40x speedup over the vanilla passage reranker. Furthermore, we introduce Sigmoid Trick, a novel loss function customized for title reranking. Combining both techniques, we empirically validated their effectiveness, achieving state-of-the-art results on all four datasets we experimented with from the KILT knowledge benchmark.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 35 of its 44 references that are in the map. First posted on arXiv 19 Dec 2023.

Builds on

35 of 44 references.

Closest ancestors · 1

Same direction, newest first

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May

Other references · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  7. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  9. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  10. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  11. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  12. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
22 more
  1. 2019Passage Re-ranking with BERTcited by 629
  2. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  3. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  4. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
  5. 2020Autoregressive Entity Retrievalcited by 333
  6. 2020Are we done with ImageNet?cited by 329
  7. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  8. 2019Multi-Stage Document Ranking with BERTcited by 200
  9. 2021RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingcited by 175
  10. 2021Condenser: a Pre-training Architecture for Dense Retrievalcited by 162
  11. 2022RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encodercited by 118
  12. 2022RankT5: Fine-Tuning T5 for Text Ranking with Ranking Lossescited by 114
  13. 2022Autoregressive Search Engines: Generating Substrings as Document Identifierscited by 112
  14. 2022FiD-Light: Efficient and Effective Retrieval-Augmented Text Generationcited by 63
  15. 2021Multi-task Retrieval for Knowledge-Intensive Taskscited by 44
  16. 2022Curriculum Learning for Dense Retrieval Distillationcited by 38
  17. 2022CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Taskscited by 36
  18. 2022PROD: Progressive Distillation for Dense Retrievalcited by 20
  19. 2022ConTextual Masked Auto-Encoder for Dense Passage Retrievalcited by 16
  20. 2022LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrievalcited by 15
  21. 2023GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Rankingcited by 11
  22. 2022LEAD: Liberal Feature-based Distillation for Dense Retrievalcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Transforming LLMs into Efficient Cross-Encoders via Knowledge Distillation for RAG Reranking
  2. 2026KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking
  3. 2025Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval
  4. 2024JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking
  5. 2025Reranking with Compressed Document Representation ↗
  6. 2025Rank1: Test-Time Compute for Reranking in Information Retrieval
  7. 2026LURE-RAG: Lightweight Utility-driven Reranking for Efficient RAG
  8. 2025The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Models