Lune

ACL Findings2021

Contrastive Fine-tuning Improves Robustness for Neural Rankers

Xiaofei Ma, Cícero Nogueira dos Santos, Andrew O. Arnold

Abstract

The performance of state-of-the-art neural rankers can deteriorate substantially when exposed to noisy inputs or applied to a new domain. In this paper, we present a novel method for fine-tuning neural rankers that can significantly improve their robustness to out-of-domain data and query perturbations. Specifically, a contrastive loss that compares data points in the representation space is combined with the standard ranking loss during fine-tuning. We use relevance labels to denote similar/dissimilar pairs, which allows the model to learn the underlying matching semantics across different query-document pairs and leads to improved robustness. In experiments with four passage ranking datasets, the proposed contrastive fine-tuning method obtains improvements on robustness to query reformulations, noise perturbations, and zeroshot transfer for both BERT and BART-based rankers. Additionally, our experiments show that contrastive fine-tuning outperforms data augmentation for robustifying neural rankers.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. A Contrastive Framework for Learning Sentence Representations from Pairwise and Triple-wise Perspective in Angular SpaceYuhao Zhang, Hongji Zhu, Yongliang Wang, Nan Xu et al.ACL 2022 · 94 citations
  2. Successive Prompting for Decomposing Complex QuestionsDheeru Dua, Shivanshu Gupta, Sameer Singh, Matt GardnerEMNLP 2022 · 38 citations
  3. UNICS: Multilingual Code Search via Unified Pseudocode and Contrastive Transfer LearningYe Fan, Jidong Ge, Chuanyi Li, LiGuo Huang et al.FSE 2026

Builds on9

  1. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
  2. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text RetrievalLee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang et al.ICLR 2021 · 1,547 citations
  3. Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and EntailmentDi Jin, Zhijing Jin, Joey Tianyi Zhou, Peter SzolovitsAAAI 2020 · 1,333 citations
  4. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  5. Learning The Difference That Makes A Difference With Counterfactually-Augmented DataDivyansh Kaushik, Eduard H. Hovy, Zachary Chase LiptonICLR 2020 · 625 citations

Related papers

  1. Towards Robust Ranker for Text RetrievalYucheng Zhou, Tao Shen, Xiubo Geng, Chongyang Tao et al.ACL Findings 2023 · 15 citations
  2. Improved Text Classification via Contrastive Adversarial TrainingLin Pan, Chung-Wei Hang, Avirup Sil, Saloni PotdarAAAI 2022 · 115 citations
  3. COCO-DR: Combating the Distribution Shift in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust LearningYue Yu, Chenyan Xiong, Si Sun, Chao Zhang et al.EMNLP 2022 · 21 citations
  4. Self-Guided Contrastive Learning for BERT Sentence RepresentationsTaeuk Kim, Kang Min Yoo, Sang-goo LeeACL 2021
  5. Semi-Siamese Bi-encoder Neural Ranking Model Using Lightweight Fine-TuningEuna Jung, Jaekeol Choi, Wonjong RheeWWW 2022 · 15 citations
Dusk over the sea between two cliffs drawn in fine vertical lines