{"total":160,"rows":[{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253,"area":null},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252,"area":null},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530,"area":null},{"id":"2212.10496","title":"Precise Zero-Shot Dense Retrieval without Relevance Labels","created":"2022-12-20","cited_by_count":517,"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":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"area":null},{"id":"2108.11896","title":"A Survey on Automated Fact-Checking","created":"2021-08-26","cited_by_count":378,"area":null},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"area":null},{"id":"2106.05707","title":"FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information","created":"2021-06-10","cited_by_count":167,"area":null},{"id":"2407.12883","title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval","created":"2024-07-16","cited_by_count":158,"area":null},{"id":"2305.13117","title":"AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web","created":"2023-05-22","cited_by_count":144,"area":null},{"id":"2112.01640","title":"MultiVerS: Improving scientific claim verification with weak supervision and full-document context","created":"2021-12-02","cited_by_count":143,"area":null},{"id":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142,"area":null},{"id":"2211.09260","title":"Task-aware Retrieval with Instructions","created":"2022-11-16","cited_by_count":107,"area":null},{"id":"2106.03794","title":"COVID-Fact: Fact Extraction and Verification of Real-World Claims on COVID-19 Pandemic","created":"2021-06-07","cited_by_count":100,"area":null},{"id":"2210.13777","title":"SciFact-Open: Towards open-domain scientific claim verification","created":"2022-10-25","cited_by_count":94,"area":null},{"id":"2110.12010","title":"ClimateBert: A Pretrained Language Model for Climate-Related Text","created":"2021-10-22","cited_by_count":90,"area":null},{"id":"2407.03618","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","created":"2024-07-04","cited_by_count":88,"area":null},{"id":"2311.09000","title":"Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers","created":"2023-11-15","cited_by_count":87,"area":null},{"id":"2109.11427","title":"Automated Fact-Checking: A Survey","created":"2021-09-23","cited_by_count":55,"area":null},{"id":"2305.14264","title":"Active Learning Principles for In-Context Learning with Large Language Models","created":"2023-05-23","cited_by_count":54,"area":null},{"id":"2305.16859","title":"Scientific Fact-Checking: A Survey of Resources and Approaches","created":"2023-05-26","cited_by_count":54,"area":null},{"id":"2210.13865","title":"Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation","created":"2022-10-25","cited_by_count":45,"area":null},{"id":"2104.00640","title":"AmbiFC: Fact-Checking Ambiguous Claims with Evidence","created":"2021-04-01","cited_by_count":38,"area":null},{"id":"2310.14564","title":"Language Models Hallucinate, but May Excel at Fact Verification","created":"2023-10-23","cited_by_count":37,"area":null},{"id":"2301.11843","title":"Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking","created":"2023-01-27","cited_by_count":35,"area":null},{"id":"2312.03014","title":"Foundation Models for Weather and Climate Data Understanding: A Comprehensive Survey","created":"2023-12-05","cited_by_count":34,"area":null},{"id":"2305.15225","title":"SAIL: Search-Augmented Instruction Learning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2104.08790","title":"Misinfo Reaction Frames: Reasoning about Readers' Reactions to News Headlines","created":"2021-04-18","cited_by_count":32,"area":null},{"id":"2304.05510","title":"chatClimate: Grounding Conversational AI in Climate Science","created":"2023-04-11","cited_by_count":32,"area":null},{"id":"2307.15770","title":"CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools","created":"2023-07-28","cited_by_count":29,"area":null},{"id":"2310.12086","title":"FactCHD: Benchmarking Fact-Conflicting Hallucination Detection","created":"2023-10-18","cited_by_count":29,"area":null},{"id":"2103.02280","title":"Simplified Data Wrangling with ir_datasets","created":"2021-03-03","cited_by_count":27,"area":null},{"id":"2110.07581","title":"Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations","created":"2021-10-14","cited_by_count":27,"area":null},{"id":"2304.03728","title":"Interpretable Unified Language Checking","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25,"area":null},{"id":"2203.06169","title":"LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval","created":"2022-03-11","cited_by_count":24,"area":null},{"id":"2408.14317","title":"Claim Verification in the Age of Large Language Models: A Survey","created":"2024-08-26","cited_by_count":24,"area":null},{"id":"2310.02932","title":"Assessing Large Language Models on Climate Information","created":"2023-10-04","cited_by_count":23,"area":null},{"id":"2406.11217","title":"WeatherQA: Can Multimodal Language Models Reason about Severe Weather?","created":"2024-06-17","cited_by_count":22,"area":null},{"id":"2410.16701","title":"ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models","created":"2024-10-22","cited_by_count":21,"area":null},{"id":"2210.15212","title":"COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning","created":"2022-10-27","cited_by_count":20,"area":null},{"id":"2401.06532","title":"INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning","created":"2024-01-12","cited_by_count":20,"area":null},{"id":"2211.10411","title":"CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval","created":"2022-11-18","cited_by_count":19,"area":null},{"id":"2407.02351","title":"Generative Large Language Models in Automated Fact-Checking: A Survey","created":"2024-07-02","cited_by_count":19,"area":null},{"id":"2407.16695","title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","created":"2024-07-23","cited_by_count":19,"area":null},{"id":"2203.10053","title":"RELIC: Retrieving Evidence for Literary Claims","created":"2022-03-18","cited_by_count":18,"area":null},{"id":"2405.16546","title":"Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration","created":"2024-05-26","cited_by_count":17,"area":null},{"id":"2305.19840","title":"BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language","created":"2023-05-31","cited_by_count":15,"area":null},{"id":"2402.14151","title":"BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives","created":"2024-02-21","cited_by_count":15,"area":null},{"id":"2212.09683","title":"Human-in-the-loop Evaluation for Early Misinformation Detection: A Case Study of COVID-19 Treatments","created":"2022-12-19","cited_by_count":14,"area":null},{"id":"2505.18366","title":"Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems","created":"2025-05-23","cited_by_count":14,"area":null},{"id":"2204.02007","title":"Fact Checking with Insufficient Evidence","created":"2022-04-05","cited_by_count":11,"area":null},{"id":"2209.00507","title":"Environmental Claim Detection","created":"2022-09-01","cited_by_count":11,"area":null},{"id":"2302.08143","title":"Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?","created":"2023-02-16","cited_by_count":11,"area":null},{"id":"2305.11052","title":"BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval","created":"2023-05-18","cited_by_count":11,"area":null},{"id":"2301.04253","title":"Towards Answering Climate Questionnaires from Unstructured Climate Reports","created":"2023-01-11","cited_by_count":10,"area":null},{"id":"2310.00259","title":"AutoHall: Automated Factuality Hallucination Dataset Generation for Large Language Models","created":"2023-09-30","cited_by_count":10,"area":null},{"id":"2311.07930","title":"It's All Relative! -- A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Prediction","created":"2023-11-14","cited_by_count":10,"area":null},{"id":"2402.02844","title":"Comparing Knowledge Sources for Open-Domain Scientific Claim Verification","created":"2024-02-05","cited_by_count":10,"area":null},{"id":"2411.05060","title":"A Guide to Misinformation Detection Data and Evaluation","created":"2024-11-07","cited_by_count":10,"area":null},{"id":"2504.10816","title":"CSPLADE: Learned Sparse Retrieval with Causal Language Models","created":"2025-04-15","cited_by_count":10,"area":null},{"id":"2206.07360","title":"SciTweets -- A Dataset and Annotation Framework for Detecting Scientific Online Discourse","created":"2022-06-15","cited_by_count":9,"area":null},{"id":"2402.14268","title":"Can Large Language Models Detect Misinformation in Scientific News Reporting?","created":"2024-02-22","cited_by_count":9,"area":null},{"id":"2405.16820","title":"Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings","created":"2024-05-27","cited_by_count":9,"area":null},{"id":"2410.07490","title":"MoDEM: Mixture of Domain Expert Models","created":"2024-10-09","cited_by_count":9,"area":null},{"id":"2308.08780","title":"Exploring Demonstration Ensembling for In-context Learning","created":"2023-08-17","cited_by_count":8,"area":null},{"id":"2312.11785","title":"Zero-Shot Fact-Checking with Semantic Triples and Knowledge Graphs","created":"2023-12-19","cited_by_count":8,"area":null},{"id":"2508.17744","title":"Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks","created":"2025-08-25","cited_by_count":8,"area":null},{"id":"2404.12041","title":"A Survey of Automatic Hallucination Evaluation on Natural Language Generation","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2503.16541","title":"Poly-FEVER: A Multilingual Fact Verification Benchmark for Hallucination Detection in Large Language Models","created":"2025-03-19","cited_by_count":7,"area":null},{"id":"2208.01009","title":"Few-shot Adaptation Works with UnpredicTable Data","created":"2022-08-01","cited_by_count":6,"area":null},{"id":"2211.09388","title":"Data-Efficient Autoregressive Document Retrieval for Fact Verification","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2302.03754","title":"Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories","created":"2023-02-07","cited_by_count":6,"area":null},{"id":"2309.06578","title":"Can Large Language Models Discern Evidence for Scientific Hypotheses? Case Studies in the Social Sciences","created":"2023-09-07","cited_by_count":6,"area":null},{"id":"2412.08329","title":"BEIR-NL: Zero-shot Information Retrieval Benchmark for the Dutch Language","created":"2024-12-11","cited_by_count":6,"area":null},{"id":"2506.20844","title":"The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Papers","created":"2025-06-25","cited_by_count":6,"area":null},{"id":"2507.07700","title":"Rethinking the Privacy of Text Embeddings: A Reproducibility Study of \"Text Embeddings Reveal (Almost) As Much As Text\"","created":"2025-07-10","cited_by_count":6,"area":null},{"id":"2110.10015","title":"DEEPAG\\'E: Answering Questions in Portuguese about the Brazilian Environment","created":"2021-10-19","cited_by_count":5,"area":null},{"id":"2208.08749","title":"Active PETs: Active Data Annotation Prioritisation for Few-Shot Claim Verification with Pattern Exploiting Training","created":"2022-08-18","cited_by_count":5,"area":null},{"id":"2212.00689","title":"CliMedBERT: A Pre-trained Language Model for Climate and Health-related Text","created":"2022-12-01","cited_by_count":5,"area":null},{"id":"2312.17055","title":"Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning","created":"2023-12-28","cited_by_count":5,"area":null},{"id":"2401.16282","title":"MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verification","created":"2024-01-29","cited_by_count":5,"area":null},{"id":"2410.03341","title":"Zero-Shot Fact Verification via Natural Logic and Large Language Models","created":"2024-10-04","cited_by_count":5,"area":null},{"id":"2504.09135","title":"Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models","created":"2025-04-12","cited_by_count":5,"area":null},{"id":"2508.12355","title":"Consensus or Conflict? Fine-Grained Evaluation of Conflicting Answers in Question-Answering","created":"2025-08-17","cited_by_count":5,"area":null},{"id":"2508.16838","title":"If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2510.24810","title":"COMMUNITYNOTES: A Dataset for Exploring the Helpfulness of Fact-Checking Explanations","created":"2025-10-28","cited_by_count":5,"area":null},{"id":"2511.22150","title":"From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures","created":"2025-11-27","cited_by_count":5,"area":null},{"id":"2602.19969","title":"ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting","created":"2026-02-23","cited_by_count":5,"area":null},{"id":"2107.14740","title":"Automatic Claim Review for Climate Science via Explanation Generation","created":"2021-07-30","cited_by_count":4,"area":null},{"id":"2309.09444","title":"Investigating Zero- and Few-shot Generalization in Fact Verification","created":"2023-09-18","cited_by_count":4,"area":null},{"id":"2401.12566","title":"Automated Fact-Checking of Climate Change Claims with Large Language Models","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2404.03623","title":"Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph","created":"2024-04-04","cited_by_count":4,"area":null},{"id":"2305.06174","title":"Analysis of Climate Campaigns on Social Media using Bayesian Model Averaging","created":"2023-05-06","cited_by_count":3,"area":null},{"id":"2305.14171","title":"In-Context Probing: Toward Building Robust Classifiers via Probing Large Language Models","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2311.01666","title":"Plot Retrieval as an Assessment of Abstract Semantic Association","created":"2023-11-03","cited_by_count":3,"area":null},{"id":"2311.15563","title":"Noisy Self-Training with Synthetic Queries for Dense Retrieval","created":"2023-11-27","cited_by_count":3,"area":null},{"id":"2404.05133","title":"EcoVerse: An Annotated Twitter Dataset for Eco-Relevance Classification, Environmental Impact Analysis, and Stance Detection","created":"2024-04-08","cited_by_count":3,"area":null},{"id":"2406.02891","title":"A Bi-metric Framework for Fast Similarity Search","created":"2024-06-05","cited_by_count":3,"area":null}],"next_cursor":"100"}