{"total":52,"rows":[{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"area":"rag"},{"id":"2102.07033","title":"PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them","created":"2021-02-13","cited_by_count":200,"area":null},{"id":"2307.16877","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","created":"2023-07-31","cited_by_count":151,"area":null},{"id":"2109.06157","title":"SituatedQA: Incorporating Extra-Linguistic Contexts into QA","created":"2021-09-13","cited_by_count":145,"area":null},{"id":"2210.02627","title":"Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering","created":"2022-10-06","cited_by_count":127,"area":"rag"},{"id":"2305.18486","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","created":"2023-05-29","cited_by_count":123,"area":null},{"id":"2305.06984","title":"Evaluating Open-Domain Question Answering in the Era of Large Language Models","created":"2023-05-11","cited_by_count":111,"area":null},{"id":"2109.04212","title":"Efficient Nearest Neighbor Language Models","created":"2021-09-09","cited_by_count":93,"area":null},{"id":"2202.07654","title":"Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation","created":"2022-02-15","cited_by_count":67,"area":null},{"id":"2104.08727","title":"GooAQ: Open Question Answering with Diverse Answer Types","created":"2021-04-18","cited_by_count":53,"area":null},{"id":"2103.12528","title":"Multilingual Autoregressive Entity Linking","created":"2021-03-23","cited_by_count":50,"area":null},{"id":"2108.06130","title":"Semantic Answer Similarity for Evaluating Question Answering Models","created":"2021-08-13","cited_by_count":47,"area":null},{"id":"2107.11976","title":"One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval","created":"2021-07-26","cited_by_count":46,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2110.07038","title":"Towards Efficient NLP: A Standard Evaluation and A Strong Baseline","created":"2021-10-13","cited_by_count":44,"area":null},{"id":"2210.16773","title":"An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks","created":"2022-10-30","cited_by_count":36,"area":"rag"},{"id":"2109.01156","title":"Challenges in Generalization in Open Domain Question Answering","created":"2021-09-02","cited_by_count":30,"area":null},{"id":"2406.18676","title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","created":"2024-06-26","cited_by_count":27,"area":"rag"},{"id":"2210.01970","title":"Evaluate & Evaluation on the Hub: Better Best Practices for Data and Model Measurements","created":"2022-09-30","cited_by_count":22,"area":null},{"id":"2210.07913","title":"Efficiently Controlling Multiple Risks with Pareto Testing","created":"2022-10-14","cited_by_count":22,"area":null},{"id":"2109.03792","title":"Highly Parallel Autoregressive Entity Linking with Discriminative Correction","created":"2021-09-08","cited_by_count":21,"area":null},{"id":"2109.05289","title":"What's in a Name? Answer Equivalence For Open-Domain Question Answering","created":"2021-09-11","cited_by_count":21,"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":"2204.04581","title":"Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering","created":"2022-04-10","cited_by_count":19,"area":"rag"},{"id":"2109.02905","title":"Exploiting Reasoning Chains for Multi-hop Science Question Answering","created":"2021-09-07","cited_by_count":15,"area":null},{"id":"2210.05769","title":"Vote'n'Rank: Revision of Benchmarking with Social Choice Theory","created":"2022-10-11","cited_by_count":15,"area":null},{"id":"2109.01048","title":"Pre-training Language Model Incorporating Domain-specific Heterogeneous Knowledge into A Unified Representation","created":"2021-09-02","cited_by_count":11,"area":null},{"id":"2110.08544","title":"Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify Framework","created":"2021-10-16","cited_by_count":11,"area":null},{"id":"2207.00758","title":"MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages","created":"2022-07-02","cited_by_count":11,"area":null},{"id":"2409.18110","title":"Open-World Evaluation for Retrieving Diverse Perspectives","created":"2024-09-26","cited_by_count":11,"area":null},{"id":"2112.07771","title":"Boosted Dense Retriever","created":"2021-12-14","cited_by_count":10,"area":null},{"id":"2211.12707","title":"Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?","created":"2022-11-23","cited_by_count":10,"area":null},{"id":"2403.05217","title":"Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering","created":"2024-03-08","cited_by_count":8,"area":null},{"id":"2307.09701","title":"Efficiency Pentathlon: A Standardized Arena for Efficiency Evaluation","created":"2023-07-19","cited_by_count":7,"area":null},{"id":"2110.09147","title":"BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation","created":"2021-10-18","cited_by_count":6,"area":null},{"id":"2104.07242","title":"Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering","created":"2021-04-15","cited_by_count":5,"area":null},{"id":"2406.10786","title":"Evaluating LLMs with Multiple Problems at once","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2201.05984","title":"In Situ Answer Sentence Selection at Web-scale","created":"2022-01-16","cited_by_count":2,"area":null},{"id":"2202.07791","title":"Russian SuperGLUE 1.1: Revising the Lessons not Learned by Russian NLP models","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2602.17663","title":"CLEF HIPE-2026: Evaluating Accurate and Efficient Person-Place Relation Extraction from Multilingual Historical Texts","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2106.06292","title":"A Discussion on Building Practical NLP Leaderboards: The Case of Machine Translation","created":"2021-06-11","cited_by_count":1,"area":null},{"id":"2206.12664","title":"Evaluation of Semantic Answer Similarity Metrics","created":"2022-06-25","cited_by_count":1,"area":null},{"id":"2206.12993","title":"Are We There Yet? A Decision Framework for Replacing Term Based Retrieval with Dense Retrieval Systems","created":"2022-06-26","cited_by_count":1,"area":null},{"id":"2210.06599","title":"Improving Question Answering with Generation of NQ-like Questions","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2210.13678","title":"Bridging the Training-Inference Gap for Dense Phrase Retrieval","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2309.12250","title":"SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative References","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2406.13232","title":"Towards Robust Evaluation: A Comprehensive Taxonomy of Datasets and Metrics for Open Domain Question Answering in the Era of Large Language Models","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2202.13581","title":"'Tis but Thy Name: Semantic Question Answering Evaluation with 11M Names for 1M Entities","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2210.04466","title":"Investigating the Failure Modes of the AUC metric and Exploring Alternatives for Evaluating Systems in Safety Critical Applications","created":"2022-10-10","cited_by_count":0,"area":null},{"id":"2406.18245","title":"Weak Reward Model Transforms Generative Models into Robust Causal Event Extraction Systems","created":"2024-06-26","cited_by_count":0,"area":"alignment"},{"id":"2607.20510","title":"Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain","created":"2026-07-04","cited_by_count":0,"area":"agents"}],"next_cursor":null}