{"total":138,"rows":[{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745,"area":"alignment"},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293,"area":null},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966,"area":null},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916,"area":null},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792,"area":"rag"},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2109.05052","title":"Entity-Based Knowledge Conflicts in Question Answering","created":"2021-09-10","cited_by_count":356,"area":null},{"id":"2106.15110","title":"Time-Aware Language Models as Temporal Knowledge Bases","created":"2021-06-29","cited_by_count":296,"area":null},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292,"area":null},{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230,"area":null},{"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":"2104.00369","title":"FeTaQA: Free-form Table Question Answering","created":"2021-04-01","cited_by_count":175,"area":null},{"id":"2110.03215","title":"Towards Continual Knowledge Learning of Language Models","created":"2021-10-07","cited_by_count":174,"area":null},{"id":"2103.06332","title":"Hurdles to Progress in Long-form Question Answering","created":"2021-03-10","cited_by_count":167,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2210.13701","title":"Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence","created":"2022-10-25","cited_by_count":144,"area":null},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"area":"lr"},{"id":"2109.08535","title":"Simple Entity-Centric Questions Challenge Dense Retrievers","created":"2021-09-17","cited_by_count":140,"area":null},{"id":"2202.03829","title":"TimeLMs: Diachronic Language Models from Twitter","created":"2022-02-08","cited_by_count":131,"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":"2305.00118","title":"Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4","created":"2023-04-28","cited_by_count":125,"area":"safety"},{"id":"2204.14211","title":"TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models","created":"2022-04-29","cited_by_count":119,"area":null},{"id":"2204.10628","title":"Autoregressive Search Engines: Generating Substrings as Document Identifiers","created":"2022-04-22","cited_by_count":113,"area":null},{"id":"2104.08762","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","created":"2021-04-18","cited_by_count":107,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2106.01515","title":"Question Answering Over Temporal Knowledge Graphs","created":"2021-06-03","cited_by_count":99,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2310.11501","title":"CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations","created":"2023-10-17","cited_by_count":97,"area":null},{"id":"2211.05655","title":"DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering","created":"2022-11-10","cited_by_count":96,"area":null},{"id":"2312.09979","title":"LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin","created":"2023-12-15","cited_by_count":82,"area":"moe"},{"id":"2104.08678","title":"Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation","created":"2021-04-18","cited_by_count":79,"area":null},{"id":"2203.08383","title":"Iteratively Prompt Pre-trained Language Models for Chain of Thought","created":"2022-03-16","cited_by_count":75,"area":"lr"},{"id":"2211.17257","title":"CREPE: Open-Domain Question Answering with False Presuppositions","created":"2022-11-30","cited_by_count":72,"area":null},{"id":"2102.01818","title":"Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation","created":"2021-02-03","cited_by_count":70,"area":null},{"id":"2210.01296","title":"Recitation-Augmented Language Models","created":"2022-10-04","cited_by_count":65,"area":null},{"id":"2403.05973","title":"Calibrating Large Language Models Using Their Generations Only","created":"2024-03-09","cited_by_count":65,"area":null},{"id":"2106.01561","title":"Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?","created":"2021-06-03","cited_by_count":62,"area":null},{"id":"2110.06918","title":"Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?","created":"2021-10-13","cited_by_count":60,"area":null},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60,"area":null},{"id":"2406.13121","title":"Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?","created":"2024-06-19","cited_by_count":56,"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":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53,"area":null},{"id":"2101.00133","title":"NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned","created":"2021-01-01","cited_by_count":52,"area":null},{"id":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2105.13947","title":"Changing the World by Changing the Data","created":"2021-05-28","cited_by_count":51,"area":null},{"id":"2112.07708","title":"Learning to Retrieve Passages without Supervision","created":"2021-12-14","cited_by_count":46,"area":null},{"id":"2101.00117","title":"Multi-task Retrieval for Knowledge-Intensive Tasks","created":"2021-01-01","cited_by_count":44,"area":null},{"id":"2407.13998","title":"RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering","created":"2024-07-19","cited_by_count":43,"area":"rag"},{"id":"2101.00178","title":"UnitedQA: A Hybrid Approach for Open Domain Question Answering","created":"2021-01-01","cited_by_count":42,"area":null},{"id":"2205.12665","title":"QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs","created":"2022-05-25","cited_by_count":42,"area":null},{"id":"2112.08688","title":"Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks","created":"2021-12-16","cited_by_count":40,"area":"rag"},{"id":"2104.12741","title":"GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrieval","created":"2021-04-26","cited_by_count":39,"area":null},{"id":"2212.08635","title":"Self-Prompting Large Language Models for Zero-Shot Open-Domain QA","created":"2022-12-16","cited_by_count":39,"area":null},{"id":"2109.03502","title":"R2-D2: A Modular Baseline for Open-Domain Question Answering","created":"2021-09-08","cited_by_count":37,"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":"2310.16570","title":"Give Me the Facts! A Survey on Factual Knowledge Probing in Pre-trained Language Models","created":"2023-10-25","cited_by_count":32,"area":null},{"id":"2104.05837","title":"Relational World Knowledge Representation in Contextual Language Models: A Review","created":"2021-04-12","cited_by_count":31,"area":null},{"id":"2109.01156","title":"Challenges in Generalization in Open Domain Question Answering","created":"2021-09-02","cited_by_count":30,"area":null},{"id":"2110.02782","title":"How BPE Affects Memorization in Transformers","created":"2021-10-06","cited_by_count":29,"area":null},{"id":"2212.10380","title":"What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2202.00395","title":"Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification","created":"2022-02-01","cited_by_count":26,"area":null},{"id":"2106.05532","title":"How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluation","created":"2021-06-10","cited_by_count":24,"area":null},{"id":"2305.08414","title":"What's the Meaning of Superhuman Performance in Today's NLU?","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2203.12171","title":"An Empirical Study of Memorization in NLP","created":"2022-03-23","cited_by_count":21,"area":null},{"id":"2201.07745","title":"Improving Biomedical Information Retrieval with Neural Retrievers","created":"2022-01-19","cited_by_count":20,"area":null},{"id":"2308.07120","title":"Position: Key Claims in LLM Research Have a Long Tail of Footnotes","created":"2023-08-14","cited_by_count":20,"area":null},{"id":"2109.00527","title":"Boosting Search Engines with Interactive Agents","created":"2021-09-01","cited_by_count":19,"area":null},{"id":"2110.04374","title":"A Few More Examples May Be Worth Billions of Parameters","created":"2021-10-08","cited_by_count":19,"area":null},{"id":"2303.14770","title":"Koala: An Index for Quantifying Overlaps with Pre-training Corpora","created":"2023-03-26","cited_by_count":19,"area":null},{"id":"2311.08106","title":"Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models","created":"2023-11-14","cited_by_count":18,"area":null},{"id":"2108.06743","title":"Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning","created":"2021-08-15","cited_by_count":17,"area":null},{"id":"2410.02719","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","created":"2024-10-03","cited_by_count":16,"area":"rag"},{"id":"2410.08385","title":"Language model developers should report train-test overlap","created":"2024-10-10","cited_by_count":16,"area":null},{"id":"2103.01242","title":"Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in Language","created":"2021-03-01","cited_by_count":15,"area":null},{"id":"2203.10232","title":"DuReader_retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine","created":"2022-03-19","cited_by_count":15,"area":null},{"id":"2403.18365","title":"BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models","created":"2024-03-27","cited_by_count":15,"area":null},{"id":"2110.06393","title":"Attention-guided Generative Models for Extractive Question Answering","created":"2021-10-12","cited_by_count":14,"area":null},{"id":"2211.08380","title":"Empowering Language Models with Knowledge Graph Reasoning for Question Answering","created":"2022-11-15","cited_by_count":14,"area":"lr"},{"id":"2110.07731","title":"CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training","created":"2021-10-14","cited_by_count":13,"area":null},{"id":"2110.08542","title":"Hey AI, Can You Solve Complex Tasks by Talking to Agents?","created":"2021-10-16","cited_by_count":13,"area":null},{"id":"2204.07408","title":"Towards Fine-grained Causal Reasoning and QA","created":"2022-04-15","cited_by_count":13,"area":"lr"},{"id":"2301.11293","title":"Understanding Finetuning for Factual Knowledge Extraction from Language Models","created":"2023-01-26","cited_by_count":13,"area":null},{"id":"2105.01974","title":"Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards","created":"2021-05-05","cited_by_count":12,"area":null},{"id":"2106.15065","title":"Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on Spoken Language Understanding","created":"2021-06-29","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":"2205.06111","title":"Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language","created":"2022-05-12","cited_by_count":10,"area":null},{"id":"2211.01587","title":"Eliciting Knowledge from Large Pre-Trained Models for Unsupervised Knowledge-Grounded Conversation","created":"2022-11-03","cited_by_count":10,"area":null},{"id":"2104.07800","title":"Towards Robust Neural Retrieval Models with Synthetic Pre-Training","created":"2021-04-15","cited_by_count":9,"area":null},{"id":"2108.00578","title":"Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning","created":"2021-08-02","cited_by_count":9,"area":null},{"id":"2210.06799","title":"Benchmarking Long-tail Generalization with Likelihood Splits","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2510.07575","title":"Benchmarking is Broken -- Don't Let AI be its Own Judge","created":"2025-10-08","cited_by_count":8,"area":null},{"id":"2205.12680","title":"Optimizing Test-Time Query Representations for Dense Retrieval","created":"2022-05-25","cited_by_count":7,"area":null},{"id":"2208.12888","title":"Investigating data partitioning strategies for crosslinguistic low-resource ASR evaluation","created":"2022-08-26","cited_by_count":7,"area":null},{"id":"2210.03273","title":"A Unified Encoder-Decoder Framework with Entity Memory","created":"2022-10-07","cited_by_count":7,"area":null},{"id":"2308.11103","title":"Anonymity at Risk? Assessing Re-Identification Capabilities of Large Language Models","created":"2023-08-22","cited_by_count":7,"area":null},{"id":"2403.01774","title":"WebCiteS: Attributed Query-Focused Summarization on Chinese Web Search Results with Citations","created":"2024-03-04","cited_by_count":7,"area":null},{"id":"2512.07497","title":"How Do LLMs Fail In Agentic Scenarios? A Qualitative Analysis of Success and Failure Scenarios of Various LLMs in Agentic Simulations","created":"2025-12-08","cited_by_count":7,"area":"agents"},{"id":"2209.15469","title":"Zero-Shot Retrieval with Search Agents and Hybrid Environments","created":"2022-09-30","cited_by_count":6,"area":"agents"},{"id":"2305.08208","title":"Learning to Generalize for Cross-domain QA","created":"2023-05-14","cited_by_count":6,"area":null},{"id":"2310.10190","title":"Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT -- A Text-to-SQL Parsing Comparison","created":"2023-10-16","cited_by_count":6,"area":null}],"next_cursor":"100"}