ExaRanker: Explanation-Augmented Neural Ranker
Not on the map. Why?
Abstract (arXiv)
Recent work has shown that inducing a large language model (LLM) to generate explanations prior to outputting an answer is an effective strategy to improve performance on a wide range of reasoning tasks. In this work, we show that neural rankers also benefit from explanations. We use LLMs such as GPT-3.5 to augment retrieval datasets with explanations and train a sequence-to-sequence ranking model to output a relevance label and an explanation for a given query-document pair. Our model, dubbed ExaRanker, finetuned on a few thousand examples with synthetic explanations performs on par with models finetuned on 3x more examples without explanations. Furthermore, the ExaRanker model incurs no additional computational cost during ranking and allows explanations to be requested on demand.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 44 of its 70 references that are in the map. First posted on arXiv 25 Jan 2023.
Builds on
44 of 70 references.
References · 44
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
- 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
- 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
- 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
- 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
- 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
- 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
- 2022Large Language Models Can Self-Improvecited by 664
- 2019Passage Re-ranking with BERTcited by 645
32 more
- 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
- 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
- 2021SPLADE: Sparse Lexical and Expansion Model for First Stage Rankingcited by 286
- 2022Teaching Small Language Models to Reasoncited by 284
- 2020Pretrained Transformers for Text Ranking: BERT and Beyondcited by 267
- 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
- 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 235
- 2021Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrievalcited by 203
- 2021Overview of the TREC 2020 deep learning trackcited by 196
- 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 165
- 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
- 2022RankT5: Fine-Tuning T5 for Text Ranking with Ranking Lossescited by 115
- 2019CEDR: Contextualized Embeddings for Document Rankingcited by 77
- 2023InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrievalcited by 73
- 2021Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipelinecited by 65
- 2020PARADE: Passage Representation Aggregation for Document Rerankingcited by 44
- 2021Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similaritycited by 35
- 2021Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representationscited by 27
- 2022Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reductioncited by 21
- 2022In Defense of Cross-Encoders for Zero-Shot Retrievalcited by 21
- 2022Learning to Scaffold: Optimizing Model Explanations for Teachingcited by 20
- 2019A study on the Interpretability of Neural Retrieval Models using DeepSHAPcited by 19
- 2018EXS: Explainable Search Using Local Model Agnostic Interpretabilitycited by 18
- 2022No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrievalcited by 17
- 2021Teaching Autoregressive Language Models Complex Tasks By Demonstrationcited by 15
- 2020Abstractive Snippet Generationcited by 11
- 2018Posthoc Interpretability of Learning to Rank Models using Secondary Training Datacited by 10
- 2022Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Modelscited by 10
- 2021Towards Axiomatic Explanations for Neural Ranking Modelscited by 7
- 2021Explaining Documents' Relevance to Search Queriescited by 5
- 2020Valid Explanations for Learning to Rank Modelscited by 4
- 2018Interpreting search result rankings through intent modelingcited by 2
Built on by
Citing papers per year: 2023: 2.
2 papers.