{"total":165,"rows":[{"id":"2402.03216","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","created":"2024-02-05","cited_by_count":1073,"area":"distill"},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723,"area":null},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692,"area":null},{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476,"area":null},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237,"area":null},{"id":"2209.11755","title":"Promptagator: Few-shot Dense Retrieval From 8 Examples","created":"2022-09-23","cited_by_count":235,"area":null},{"id":"2108.11601","title":"Retrieval Augmented Code Generation and Summarization","created":"2021-08-26","cited_by_count":149,"area":"rag"},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2112.07577","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","created":"2021-12-14","cited_by_count":119,"area":null},{"id":"2104.07186","title":"COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List","created":"2021-04-15","cited_by_count":113,"area":null},{"id":"2203.13224","title":"Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion","created":"2022-03-24","cited_by_count":102,"area":null},{"id":"2205.09707","title":"PLAID: An Efficient Engine for Late Interaction Retrieval","created":"2022-05-19","cited_by_count":101,"area":null},{"id":"2104.08027","title":"Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders","created":"2021-04-16","cited_by_count":88,"area":null},{"id":"2109.04650","title":"What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers","created":"2021-09-10","cited_by_count":76,"area":null},{"id":"2405.13401","title":"TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models","created":"2024-05-22","cited_by_count":67,"area":"rag"},{"id":"2305.18846","title":"Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation","created":"2023-05-30","cited_by_count":54,"area":null},{"id":"2206.10658","title":"Questions Are All You Need to Train a Dense Passage Retriever","created":"2022-06-21","cited_by_count":47,"area":null},{"id":"2212.01588","title":"RHO ($\\rho$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding","created":"2022-12-03","cited_by_count":47,"area":null},{"id":"2103.05284","title":"Open-book Video Captioning with Retrieve-Copy-Generate Network","created":"2021-03-09","cited_by_count":43,"area":null},{"id":"2203.08372","title":"Multi-View Document Representation Learning for Open-Domain Dense Retrieval","created":"2022-03-16","cited_by_count":41,"area":null},{"id":"2104.06245","title":"Understanding Hard Negatives in Noise Contrastive Estimation","created":"2021-04-13","cited_by_count":39,"area":null},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2111.08366","title":"Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity","created":"2021-11-16","cited_by_count":35,"area":null},{"id":"2109.08133","title":"Phrase Retrieval Learns Passage Retrieval, Too","created":"2021-09-16","cited_by_count":33,"area":null},{"id":"2110.04541","title":"The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design","created":"2021-10-09","cited_by_count":33,"area":null},{"id":"2204.10825","title":"Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterances","created":"2022-04-22","cited_by_count":32,"area":null},{"id":"2304.01982","title":"Rethinking the Role of Token Retrieval in Multi-Vector Retrieval","created":"2023-04-04","cited_by_count":31,"area":null},{"id":"2212.10423","title":"Fine-Grained Distillation for Long Document Retrieval","created":"2022-12-20","cited_by_count":29,"area":"distill"},{"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":"2103.11920","title":"Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval","created":"2021-03-22","cited_by_count":28,"area":null},{"id":"2205.00176","title":"Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models","created":"2022-04-30","cited_by_count":26,"area":null},{"id":"2306.07206","title":"RECAP: Retrieval-Enhanced Context-Aware Prefix Encoder for Personalized Dialogue Response Generation","created":"2023-06-12","cited_by_count":25,"area":null},{"id":"2110.01529","title":"A Proposed Conceptual Framework for a Representational Approach to Information Retrieval","created":"2021-10-04","cited_by_count":24,"area":null},{"id":"2208.14565","title":"Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning","created":"2022-08-30","cited_by_count":24,"area":null},{"id":"2305.17388","title":"MPCHAT: Towards Multimodal Persona-Grounded Conversation","created":"2023-05-27","cited_by_count":24,"area":null},{"id":"2109.01242","title":"Entity Linking and Discovery via Arborescence-based Supervised Clustering","created":"2021-09-02","cited_by_count":22,"area":null},{"id":"2112.05843","title":"Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an Identity","created":"2021-12-10","cited_by_count":22,"area":null},{"id":"2112.11031","title":"On Cross-Lingual Retrieval with Multilingual Text Encoders","created":"2021-12-21","cited_by_count":22,"area":null},{"id":"2401.08358","title":"Hallucination Detection and Hallucination Mitigation: An Investigation","created":"2024-01-16","cited_by_count":21,"area":null},{"id":"2109.13059","title":"Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations","created":"2021-09-27","cited_by_count":20,"area":null},{"id":"2201.07745","title":"Improving Biomedical Information Retrieval with Neural Retrievers","created":"2022-01-19","cited_by_count":20,"area":null},{"id":"2211.07886","title":"A Survey for Efficient Open Domain Question Answering","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2205.11194","title":"UnifieR: A Unified Retriever for Large-Scale Retrieval","created":"2022-05-23","cited_by_count":19,"area":null},{"id":"2206.14719","title":"Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision","created":"2022-06-29","cited_by_count":18,"area":null},{"id":"2107.11879","title":"Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration","created":"2021-07-25","cited_by_count":17,"area":null},{"id":"2202.13876","title":"PMC-Patients: A Large-scale Dataset of Patient Summaries and Relations for Benchmarking Retrieval-based Clinical Decision Support Systems","created":"2022-02-28","cited_by_count":17,"area":null},{"id":"2301.04871","title":"Learning to Memorize Entailment and Discourse Relations for Persona-Consistent Dialogues","created":"2023-01-12","cited_by_count":17,"area":null},{"id":"2106.05894","title":"Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation","created":"2021-06-10","cited_by_count":16,"area":null},{"id":"2305.14232","title":"Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding","created":"2023-05-23","cited_by_count":16,"area":null},{"id":"2106.04279","title":"Staircase Attention for Recurrent Processing of Sequences","created":"2021-06-08","cited_by_count":14,"area":null},{"id":"2304.13649","title":"A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2202.13196","title":"Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning","created":"2022-02-26","cited_by_count":13,"area":null},{"id":"2311.18213","title":"Beyond Two-Tower Matching: Learning Sparse Retrievable Cross-Interactions for Recommendation","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2103.03125","title":"Advances in Multi-turn Dialogue Comprehension: A Survey","created":"2021-03-04","cited_by_count":12,"area":null},{"id":"2207.00494","title":"Learning Job Titles Similarity from Noisy Skill Labels","created":"2022-07-01","cited_by_count":12,"area":null},{"id":"2301.04283","title":"MGeo: Multi-Modal Geographic Pre-Training Method","created":"2023-01-11","cited_by_count":12,"area":null},{"id":"2110.06612","title":"Exploring Dense Retrieval for Dialogue Response Selection","created":"2021-10-13","cited_by_count":11,"area":null},{"id":"2203.07665","title":"One Agent To Rule Them All: Towards Multi-agent Conversational AI","created":"2022-03-15","cited_by_count":11,"area":null},{"id":"2112.07771","title":"Boosted Dense Retriever","created":"2021-12-14","cited_by_count":10,"area":null},{"id":"2204.08952","title":"Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies","created":"2022-04-19","cited_by_count":10,"area":null},{"id":"2105.02978","title":"Graph-based Multilingual Product Retrieval in E-commerce Search","created":"2021-05-06","cited_by_count":9,"area":null},{"id":"2110.03262","title":"Situated Dialogue Learning through Procedural Environment Generation","created":"2021-10-07","cited_by_count":9,"area":null},{"id":"2203.05877","title":"A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings","created":"2022-03-11","cited_by_count":9,"area":null},{"id":"2211.10991","title":"Modeling Fine-grained Information via Knowledge-aware Hierarchical Graph for Zero-shot Entity Retrieval","created":"2022-11-20","cited_by_count":9,"area":null},{"id":"2305.13915","title":"DAPR: A Benchmark on Document-Aware Passage Retrieval","created":"2023-05-23","cited_by_count":9,"area":null},{"id":"2204.08173","title":"TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval","created":"2022-04-18","cited_by_count":8,"area":null},{"id":"2209.03632","title":"AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog","created":"2022-09-08","cited_by_count":8,"area":null},{"id":"2301.02401","title":"You Truly Understand What I Need: Intellectual and Friendly Dialogue Agents grounding Knowledge and Persona","created":"2023-01-06","cited_by_count":8,"area":"agents"},{"id":"2301.06400","title":"Opening up Minds with Argumentative Dialogues","created":"2023-01-16","cited_by_count":8,"area":null},{"id":"2411.11767","title":"Drowning in Documents: Consequences of Scaling Reranker Inference","created":"2024-11-18","cited_by_count":8,"area":null},{"id":"2112.03210","title":"Contextual Bandit Applications in Customer Support Bot","created":"2021-12-06","cited_by_count":7,"area":null},{"id":"2210.16953","title":"Improving Bilingual Lexicon Induction with Cross-Encoder Reranking","created":"2022-10-30","cited_by_count":7,"area":null},{"id":"2305.13199","title":"Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervision","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2306.10231","title":"GLIMMER: generalized late-interaction memory reranker","created":"2023-06-17","cited_by_count":7,"area":null},{"id":"2409.14672","title":"Speechworthy Instruction-tuned Language Models","created":"2024-09-23","cited_by_count":7,"area":null},{"id":"2410.15801","title":"Improve Dense Passage Retrieval with Entailment Tuning","created":"2024-10-21","cited_by_count":7,"area":"rag"},{"id":"2103.04156","title":"Improving Zero-Shot Entity Retrieval through Effective Dense Representations","created":"2021-03-06","cited_by_count":6,"area":null},{"id":"2112.05346","title":"Findings on Conversation Disentanglement","created":"2021-12-10","cited_by_count":6,"area":null},{"id":"2204.08415","title":"Exploring Dimensionality Reduction Techniques in Multilingual Transformers","created":"2022-04-18","cited_by_count":6,"area":null},{"id":"2205.02795","title":"Diversifying Neural Dialogue Generation via Negative Distillation","created":"2022-05-05","cited_by_count":6,"area":null},{"id":"2211.01467","title":"Generative Entity-to-Entity Stance Detection with Knowledge Graph Augmentation","created":"2022-11-02","cited_by_count":6,"area":null},{"id":"2410.19301","title":"Any Other Thoughts, Hedgehog? Linking Deliberation Chains in Collaborative Dialogues","created":"2024-10-25","cited_by_count":6,"area":null},{"id":"2507.08336","title":"Distillation versus Contrastive Learning: How to Train Your Rerankers","created":"2025-07-11","cited_by_count":6,"area":"distill"},{"id":"2205.08012","title":"CascadER: Cross-Modal Cascading for Knowledge Graph Link Prediction","created":"2022-05-16","cited_by_count":5,"area":null},{"id":"2310.04407","title":"Policy-Gradient Training of Language Models for Ranking","created":"2023-10-06","cited_by_count":5,"area":null},{"id":"2507.18202","title":"Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection","created":"2025-07-24","cited_by_count":5,"area":"rag"},{"id":"2601.01684","title":"LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum","created":"2026-01-04","cited_by_count":5,"area":null},{"id":"2108.12582","title":"Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation","created":"2021-08-28","cited_by_count":4,"area":null},{"id":"2208.04232","title":"Learning Diverse Document Representations with Deep Query Interactions for Dense Retrieval","created":"2022-08-08","cited_by_count":4,"area":null},{"id":"2307.09274","title":"Improving Text Semantic Similarity Modeling through a 3D Siamese Network","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2401.00165","title":"Mitigating the Impact of False Negatives in Dense Retrieval with Contrastive Confidence Regularization","created":"2023-12-30","cited_by_count":4,"area":null},{"id":"2404.01490","title":"AAdaM at SemEval-2024 Task 1: Augmentation and Adaptation for Multilingual Semantic Textual Relatedness","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2404.08949","title":"Multimodal Cross-Document Event Coreference Resolution Using Linear Semantic Transfer and Mixed-Modality Ensembles","created":"2024-04-13","cited_by_count":4,"area":null},{"id":"2406.06839","title":"EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction","created":"2024-06-10","cited_by_count":4,"area":null},{"id":"2407.09395","title":"Deep Bag-of-Words Model: An Efficient and Interpretable Relevance Architecture for Chinese E-Commerce","created":"2024-07-12","cited_by_count":4,"area":null},{"id":"2411.13045","title":"Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning","created":"2024-11-20","cited_by_count":4,"area":"distill"},{"id":"2109.06538","title":"Challenging Instances are Worth Learning: Generating Valuable Negative Samples for Response Selection Training","created":"2021-09-14","cited_by_count":3,"area":null},{"id":"2112.04195","title":"VIRT: Improving Representation-based Models for Text Matching through Virtual Interaction","created":"2021-12-08","cited_by_count":3,"area":null},{"id":"2112.06723","title":"Understanding and Improving the Exemplar-based Generation for Open-domain Conversation","created":"2021-12-13","cited_by_count":3,"area":null},{"id":"2204.07679","title":"DialAug: Mixing up Dialogue Contexts in Contrastive Learning for Robust Conversational Modeling","created":"2022-04-15","cited_by_count":3,"area":null}],"next_cursor":"100"}