{"total":34,"rows":[{"id":"2108.13897","title":"mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset","created":"2021-08-31","cited_by_count":116,"area":null},{"id":"2312.15503","title":"Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval","created":"2023-12-24","cited_by_count":78,"area":null},{"id":"2208.07652","title":"CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks","created":"2022-08-16","cited_by_count":36,"area":null},{"id":"2305.19249","title":"Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models","created":"2023-05-30","cited_by_count":29,"area":null},{"id":"2308.09861","title":"Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method","created":"2023-08-19","cited_by_count":29,"area":null},{"id":"2105.04021","title":"MS MARCO: Benchmarking Ranking Models in the Large-Data Regime","created":"2021-05-09","cited_by_count":28,"area":null},{"id":"2204.02363","title":"Towards Best Practices for Training Multilingual Dense Retrieval Models","created":"2022-04-05","cited_by_count":26,"area":null},{"id":"2407.09417","title":"Mitigating Entity-Level Hallucination in Large Language Models","created":"2024-07-12","cited_by_count":17,"area":null},{"id":"2312.10661","title":"Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval","created":"2023-12-17","cited_by_count":15,"area":null},{"id":"2208.03197","title":"Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey","created":"2022-08-05","cited_by_count":14,"area":null},{"id":"2305.05393","title":"CaseEncoder: A Knowledge-enhanced Pre-trained Model for Legal Case Encoding","created":"2023-05-09","cited_by_count":14,"area":null},{"id":"2404.01574","title":"Multi-granular Adversarial Attacks against Black-box Neural Ranking Models","created":"2024-04-02","cited_by_count":14,"area":null},{"id":"2305.02564","title":"RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2204.02725","title":"Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning","created":"2022-04-06","cited_by_count":10,"area":null},{"id":"2306.06707","title":"QUERT: Continual Pre-training of Language Model for Query Understanding in Travel Domain Search","created":"2023-06-11","cited_by_count":10,"area":null},{"id":"2205.01886","title":"P^3 Ranker: Mitigating the Gaps between Pre-training and Ranking Fine-tuning with Prompt-based Learning and Pre-finetuning","created":"2022-05-04","cited_by_count":7,"area":null},{"id":"2312.10329","title":"Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off","created":"2023-12-16","cited_by_count":7,"area":null},{"id":"2304.07946","title":"Learning To Rank Resources with GNN","created":"2023-04-17","cited_by_count":6,"area":null},{"id":"2208.10226","title":"From Easy to Hard: A Dual Curriculum Learning Framework for Context-Aware Document Ranking","created":"2022-08-22","cited_by_count":5,"area":null},{"id":"2208.05753","title":"Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval","created":"2022-08-11","cited_by_count":4,"area":null},{"id":"2212.08841","title":"AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentation","created":"2022-12-17","cited_by_count":3,"area":null},{"id":"2301.10444","title":"An Experimental Study on Pretraining Transformers from Scratch for IR","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2108.05652","title":"Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm","created":"2021-08-12","cited_by_count":2,"area":null},{"id":"2209.06583","title":"Pre-training for Information Retrieval: Are Hyperlinks Fully Explored?","created":"2022-09-14","cited_by_count":2,"area":null},{"id":"2505.07166","title":"Pre-training vs. Fine-tuning: A Reproducibility Study on Dense Retrieval Knowledge Acquisition","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2109.06436","title":"YES SIR!Optimizing Semantic Space of Negatives with Self-Involvement Ranker","created":"2021-09-14","cited_by_count":1,"area":null},{"id":"2204.11545","title":"LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2207.04656","title":"Topic-Grained Text Representation-based Model for Document Retrieval","created":"2022-07-11","cited_by_count":0,"area":null},{"id":"2306.10056","title":"Generate to Understand for Representation","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2311.07204","title":"On Elastic Language Models","created":"2023-11-13","cited_by_count":0,"area":null},{"id":"2311.15790","title":"A Social-aware Gaussian Pre-trained Model for Effective Cold-start Recommendation","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2402.02932","title":"Domain Adaptation of Multilingual Semantic Search -- Literature Review","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2403.16915","title":"Coarse-Tuning for Ad-hoc Document Retrieval Using Pre-trained Language Models","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2510.10224","title":"Text2Token: Unsupervised Text Representation Learning with Token Target Prediction","created":"2025-10-11","cited_by_count":0,"area":null}],"next_cursor":null}