{"total":295,"rows":[{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418,"area":null},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878,"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":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2108.11896","title":"A Survey on Automated Fact-Checking","created":"2021-08-26","cited_by_count":378,"area":null},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2310.03716","title":"A Long Way to Go: Investigating Length Correlations in RLHF","created":"2023-10-05","cited_by_count":291,"area":"alignment"},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"area":null},{"id":"2103.08541","title":"Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence","created":"2021-03-15","cited_by_count":225,"area":null},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202,"area":null},{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194,"area":null},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178,"area":null},{"id":"2104.06644","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","created":"2021-04-14","cited_by_count":177,"area":null},{"id":"2305.14552","title":"Sources of Hallucination by Large Language Models on Inference Tasks","created":"2023-05-23","cited_by_count":169,"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":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126,"area":null},{"id":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125,"area":null},{"id":"2303.01432","title":"WiCE: Real-World Entailment for Claims in Wikipedia","created":"2023-03-02","cited_by_count":120,"area":null},{"id":"2108.06712","title":"HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation","created":"2021-08-15","cited_by_count":118,"area":"lr"},{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"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":"2209.06293","title":"Do Androids Laugh at Electric Sheep? Humor \"Understanding\" Benchmarks from The New Yorker Caption Contest","created":"2022-09-13","cited_by_count":98,"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":"2104.08646","title":"Competency Problems: On Finding and Removing Artifacts in Language Data","created":"2021-04-17","cited_by_count":91,"area":null},{"id":"2106.09248","title":"X-FACT: A New Benchmark Dataset for Multilingual Fact Checking","created":"2021-06-17","cited_by_count":91,"area":null},{"id":"2207.10062","title":"DataPerf: Benchmarks for Data-Centric AI Development","created":"2022-07-20","cited_by_count":90,"area":null},{"id":"2109.01653","title":"CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge","created":"2021-09-03","cited_by_count":88,"area":null},{"id":"2204.04907","title":"Same Author or Just Same Topic? Towards Content-Independent Style Representations","created":"2022-04-11","cited_by_count":86,"area":null},{"id":"2205.12404","title":"FLUTE: Figurative Language Understanding through Textual Explanations","created":"2022-05-24","cited_by_count":79,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2106.00245","title":"Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models","created":"2021-06-01","cited_by_count":75,"area":null},{"id":"2106.09449","title":"DocNLI: A Large-scale Dataset for Document-level Natural Language Inference","created":"2021-06-17","cited_by_count":75,"area":null},{"id":"2308.11696","title":"Efficient Benchmarking of Language Models","created":"2023-08-22","cited_by_count":71,"area":null},{"id":"2402.12483","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","created":"2024-02-19","cited_by_count":71,"area":null},{"id":"2202.06856","title":"Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization","created":"2022-02-14","cited_by_count":69,"area":null},{"id":"2110.01518","title":"Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics","created":"2021-10-04","cited_by_count":67,"area":null},{"id":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66,"area":null},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2203.12990","title":"Generating Scientific Claims for Zero-Shot Scientific Fact Checking","created":"2022-03-24","cited_by_count":59,"area":null},{"id":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58,"area":null},{"id":"2207.14251","title":"Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions","created":"2022-07-28","cited_by_count":57,"area":null},{"id":"2105.04949","title":"BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?","created":"2021-05-11","cited_by_count":56,"area":null},{"id":"2111.00607","title":"A Systematic Investigation of Commonsense Knowledge in Large Language Models","created":"2021-10-31","cited_by_count":56,"area":null},{"id":"2405.09605","title":"Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models","created":"2024-05-15","cited_by_count":55,"area":"wm"},{"id":"2203.12942","title":"Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets","created":"2022-03-24","cited_by_count":54,"area":null},{"id":"2106.05469","title":"Variational Information Bottleneck for Effective Low-Resource Fine-Tuning","created":"2021-06-10","cited_by_count":51,"area":null},{"id":"2104.04725","title":"Fool Me Twice: Entailment from Wikipedia Gamification","created":"2021-04-10","cited_by_count":50,"area":null},{"id":"2305.13299","title":"Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations","created":"2023-05-22","cited_by_count":49,"area":null},{"id":"2311.08648","title":"Explore Spurious Correlations at the Concept Level in Language Models for Text Classification","created":"2023-11-15","cited_by_count":48,"area":null},{"id":"2205.00415","title":"Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions","created":"2022-05-01","cited_by_count":47,"area":null},{"id":"2106.06823","title":"Prompting Contrastive Explanations for Commonsense Reasoning Tasks","created":"2021-06-12","cited_by_count":45,"area":null},{"id":"2101.03453","title":"BERT & Family Eat Word Salad: Experiments with Text Understanding","created":"2021-01-10","cited_by_count":44,"area":null},{"id":"2204.07447","title":"Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters","created":"2022-04-15","cited_by_count":44,"area":null},{"id":"2106.00969","title":"COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2310.10628","title":"Data Contamination Through the Lens of Time","created":"2023-10-16","cited_by_count":40,"area":null},{"id":"2109.00087","title":"It's not Rocket Science : Interpreting Figurative Language in Narratives","created":"2021-08-31","cited_by_count":39,"area":null},{"id":"2110.10101","title":"Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition","created":"2021-10-19","cited_by_count":35,"area":null},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35,"area":null},{"id":"2107.09846","title":"Guided Generation of Cause and Effect","created":"2021-07-21","cited_by_count":33,"area":null},{"id":"2104.08161","title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2203.10995","title":"Word Order Does Matter (And Shuffled Language Models Know It)","created":"2022-03-21","cited_by_count":32,"area":null},{"id":"2304.09138","title":"Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task","created":"2023-04-18","cited_by_count":32,"area":null},{"id":"2106.00872","title":"On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2310.13486","title":"Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning","created":"2023-10-20","cited_by_count":31,"area":null},{"id":"2212.10534","title":"DISCO: Distilling Counterfactuals with Large Language Models","created":"2022-12-20","cited_by_count":30,"area":null},{"id":"2104.07179","title":"Does Putting a Linguist in the Loop Improve NLU Data Collection?","created":"2021-04-15","cited_by_count":29,"area":null},{"id":"2104.08142","title":"Supervising Model Attention with Human Explanations for Robust Natural Language Inference","created":"2021-04-16","cited_by_count":29,"area":null},{"id":"2511.04655","title":"Benchmark Designers Should \"Train on the Test Set\" to Expose Exploitable Non-Visual Shortcuts","created":"2025-11-06","cited_by_count":29,"area":"mllm"},{"id":"2104.08825","title":"Flexible Generation of Natural Language Deductions","created":"2021-04-18","cited_by_count":28,"area":null},{"id":"2104.10343","title":"Sensitivity as a Complexity Measure for Sequence Classification Tasks","created":"2021-04-21","cited_by_count":28,"area":null},{"id":"2210.14011","title":"Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens","created":"2022-10-25","cited_by_count":28,"area":null},{"id":"2105.05912","title":"MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation","created":"2021-05-12","cited_by_count":27,"area":"distill"},{"id":"2305.14910","title":"From Shortcuts to Triggers: Backdoor Defense with Denoised PoE","created":"2023-05-24","cited_by_count":27,"area":null},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2205.01376","title":"Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning","created":"2022-05-03","cited_by_count":25,"area":null},{"id":"2211.15649","title":"Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2305.04990","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2503.11751","title":"reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs","created":"2025-03-14","cited_by_count":25,"area":"alignment"},{"id":"2105.10188","title":"Semantic Representation for Dialogue Modeling","created":"2021-05-21","cited_by_count":24,"area":null},{"id":"2109.02071","title":"End-to-End Self-Debiasing Framework for Robust NLU Training","created":"2021-09-05","cited_by_count":24,"area":null},{"id":"2110.08514","title":"Analyzing Dynamic Adversarial Training Data in the Limit","created":"2021-10-16","cited_by_count":24,"area":null},{"id":"2110.14566","title":"IndoNLI: A Natural Language Inference Dataset for Indonesian","created":"2021-10-27","cited_by_count":24,"area":null},{"id":"2403.00393","title":"TRUCE: Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMs","created":"2024-03-01","cited_by_count":24,"area":null},{"id":"2106.00794","title":"What Ingredients Make for an Effective Crowdsourcing Protocol for Difficult NLU Data Collection Tasks?","created":"2021-06-01","cited_by_count":23,"area":null},{"id":"2109.04144","title":"Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning","created":"2021-09-09","cited_by_count":23,"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":"2312.04127","title":"Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak","created":"2023-12-07","cited_by_count":23,"area":"safety"},{"id":"2103.03872","title":"Rissanen Data Analysis: Examining Dataset Characteristics via Description Length","created":"2021-03-05","cited_by_count":22,"area":null},{"id":"2109.08256","title":"Ethics Sheet for Automatic Emotion Recognition and Sentiment Analysis","created":"2021-09-17","cited_by_count":22,"area":null},{"id":"2310.19660","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2204.04487","title":"Informativeness and Invariance: Two Perspectives on Spurious Correlations in Natural Language","created":"2022-04-09","cited_by_count":21,"area":null},{"id":"2104.10247","title":"Modeling Event Plausibility with Consistent Conceptual Abstraction","created":"2021-04-20","cited_by_count":20,"area":null},{"id":"2106.00510","title":"CIDER: Commonsense Inference for Dialogue Explanation and Reasoning","created":"2021-06-01","cited_by_count":20,"area":null},{"id":"2404.04963","title":"SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials","created":"2024-04-07","cited_by_count":20,"area":null},{"id":"2107.11610","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","created":"2021-07-24","cited_by_count":19,"area":null},{"id":"2109.04947","title":"Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding","created":"2021-09-10","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":"2202.07280","title":"Saving Dense Retriever from Shortcut Dependency in Conversational Search","created":"2022-02-15","cited_by_count":19,"area":null}],"next_cursor":"100"}