{"total":214,"rows":[{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234,"area":null},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203,"area":null},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185,"area":null},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145,"area":null},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142,"area":null},{"id":"2210.13966","title":"The Debate Over Understanding in AI's Large Language Models","created":"2022-10-14","cited_by_count":142,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2103.11943","title":"BERT: A Review of Applications in Natural Language Processing and Understanding","created":"2021-03-22","cited_by_count":109,"area":null},{"id":"2403.02839","title":"An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4","created":"2024-03-05","cited_by_count":94,"area":null},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2103.06922","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models","created":"2021-03-11","cited_by_count":78,"area":null},{"id":"2211.08073","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","created":"2022-11-15","cited_by_count":72,"area":null},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66,"area":null},{"id":"2106.12674","title":"Fairness via Representation Neutralization","created":"2021-06-23","cited_by_count":63,"area":null},{"id":"2111.00898","title":"Availability Attacks Create Shortcuts","created":"2021-11-01","cited_by_count":62,"area":null},{"id":"2209.01515","title":"Do Large Language Models know what humans know?","created":"2022-09-04","cited_by_count":60,"area":null},{"id":"2106.00840","title":"Comparing Test Sets with Item Response Theory","created":"2021-06-01","cited_by_count":57,"area":null},{"id":"2309.08534","title":"Towards Last-layer Retraining for Group Robustness with Fewer Annotations","created":"2023-09-15","cited_by_count":54,"area":null},{"id":"2206.09917","title":"Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models","created":"2022-06-20","cited_by_count":51,"area":null},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2212.01488","title":"Event knowledge in large language models: the gap between the impossible and the unlikely","created":"2022-12-02","cited_by_count":45,"area":null},{"id":"2410.22770","title":"InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models","created":"2024-10-30","cited_by_count":42,"area":"safety"},{"id":"2110.07803","title":"Attacking Open-domain Question Answering by Injecting Misinformation","created":"2021-10-15","cited_by_count":41,"area":null},{"id":"2308.03762","title":"GPT-4 Can't Reason","created":"2023-07-21","cited_by_count":40,"area":"lr"},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2204.04541","title":"KOBEST: Korean Balanced Evaluation of Significant Tasks","created":"2022-04-09","cited_by_count":37,"area":null},{"id":"2311.07470","title":"Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers","created":"2023-11-13","cited_by_count":36,"area":"mllm"},{"id":"2203.08055","title":"Modular and Parameter-Efficient Multimodal Fusion with Prompting","created":"2022-03-15","cited_by_count":35,"area":null},{"id":"2310.00836","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","created":"2023-10-02","cited_by_count":35,"area":"lr"},{"id":"2110.08455","title":"Knowledge Enhanced Pretrained Language Models: A Compreshensive Survey","created":"2021-10-16","cited_by_count":33,"area":null},{"id":"2212.10341","title":"CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive Learning","created":"2022-12-20","cited_by_count":33,"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":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2404.16966","title":"Examining the robustness of LLM evaluation to the distributional assumptions of benchmarks","created":"2024-04-25","cited_by_count":31,"area":null},{"id":"2106.02559","title":"Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing","created":"2021-06-04","cited_by_count":28,"area":null},{"id":"2305.16572","title":"Counterfactual reasoning: Testing language models' understanding of hypothetical scenarios","created":"2023-05-26","cited_by_count":27,"area":"lr"},{"id":"2210.12814","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","created":"2022-10-23","cited_by_count":26,"area":null},{"id":"2305.07982","title":"Zero-shot Faithful Factual Error Correction","created":"2023-05-13","cited_by_count":26,"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":"2408.08041","title":"The Clever Hans Effect in Unsupervised Learning","created":"2024-08-15","cited_by_count":24,"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":"2308.10502","title":"GradientCoin: A Peer-to-Peer Decentralized Large Language Models","created":"2023-08-21","cited_by_count":23,"area":null},{"id":"2205.12466","title":"Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning","created":"2022-05-25","cited_by_count":20,"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":"2205.05535","title":"Clinical Prompt Learning with Frozen Language Models","created":"2022-05-11","cited_by_count":19,"area":null},{"id":"2302.09170","title":"KILM: Knowledge Injection into Encoder-Decoder Language Models","created":"2023-02-17","cited_by_count":19,"area":null},{"id":"2105.07571","title":"Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes","created":"2021-05-17","cited_by_count":18,"area":null},{"id":"2105.12995","title":"ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning","created":"2021-05-27","cited_by_count":18,"area":null},{"id":"2202.09662","title":"Reward Modeling for Mitigating Toxicity in Transformer-based Language Models","created":"2022-02-19","cited_by_count":18,"area":"alignment"},{"id":"2208.07316","title":"MENLI: Robust Evaluation Metrics from Natural Language Inference","created":"2022-08-15","cited_by_count":18,"area":null},{"id":"2308.07336","title":"Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic","created":"2023-08-11","cited_by_count":18,"area":"lr"},{"id":"2411.12785","title":"Joint Vision-Language Social Bias Removal for CLIP","created":"2024-11-19","cited_by_count":18,"area":null},{"id":"2107.00281","title":"Scientia Potentia Est -- On the Role of Knowledge in Computational Argumentation","created":"2021-07-01","cited_by_count":17,"area":null},{"id":"2109.04775","title":"A Strong Baseline for Query Efficient Attacks in a Black Box Setting","created":"2021-09-10","cited_by_count":16,"area":null},{"id":"2205.12640","title":"Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing","created":"2022-05-25","cited_by_count":16,"area":null},{"id":"2305.14020","title":"Does ChatGPT have Theory of Mind?","created":"2023-05-23","cited_by_count":16,"area":null},{"id":"2110.08413","title":"Invariant Language Modeling","created":"2021-10-16","cited_by_count":15,"area":null},{"id":"2206.10816","title":"Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming","created":"2022-06-22","cited_by_count":15,"area":null},{"id":"2210.11560","title":"Finding Dataset Shortcuts with Grammar Induction","created":"2022-10-20","cited_by_count":15,"area":null},{"id":"2405.15077","title":"Eliciting Informative Text Evaluations with Large Language Models","created":"2024-05-23","cited_by_count":15,"area":null},{"id":"2504.12691","title":"Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2104.08639","title":"AM2iCo: Evaluating Word Meaning in Context across Low-Resource Languages with Adversarial Examples","created":"2021-04-17","cited_by_count":14,"area":null},{"id":"2206.08567","title":"Rectify ViT Shortcut Learning by Visual Saliency","created":"2022-06-17","cited_by_count":14,"area":null},{"id":"2207.09705","title":"Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction","created":"2022-07-20","cited_by_count":14,"area":"offlinerl"},{"id":"2108.06665","title":"Accurate, yet inconsistent? Consistency Analysis on Language Understanding Models","created":"2021-08-15","cited_by_count":13,"area":null},{"id":"2205.12593","title":"Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2102.04310","title":"The Singleton Fallacy: Why Current Critiques of Language Models Miss the Point","created":"2021-02-08","cited_by_count":12,"area":null},{"id":"2110.08419","title":"Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding","created":"2021-10-16","cited_by_count":12,"area":null},{"id":"2205.09295","title":"Are Prompt-based Models Clueless?","created":"2022-05-19","cited_by_count":11,"area":null},{"id":"2301.13844","title":"Do Multi-Document Summarization Models Synthesize?","created":"2023-01-31","cited_by_count":11,"area":null},{"id":"2412.01113","title":"LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics","created":"2024-12-02","cited_by_count":11,"area":"lr"},{"id":"2105.04505","title":"Towards Benchmarking the Utility of Explanations for Model Debugging","created":"2021-05-10","cited_by_count":10,"area":null},{"id":"2205.03815","title":"Beyond Distributional Hypothesis: Let Language Models Learn Meaning-Text Correspondence","created":"2022-05-08","cited_by_count":10,"area":null},{"id":"2405.12621","title":"Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan Acquisition","created":"2024-05-21","cited_by_count":10,"area":null},{"id":"2409.17455","title":"Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models","created":"2024-09-26","cited_by_count":10,"area":null},{"id":"2412.00765","title":"SelfPrompt: Autonomously Evaluating LLM Robustness via Domain-Constrained Knowledge Guidelines and Refined Adversarial Prompts","created":"2024-12-01","cited_by_count":10,"area":"safety"},{"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":"2109.04867","title":"Studying word order through iterative shuffling","created":"2021-09-10","cited_by_count":9,"area":null},{"id":"2310.05163","title":"An Investigation of LLMs' Inefficacy in Understanding Converse Relations","created":"2023-10-08","cited_by_count":9,"area":null},{"id":"2409.14572","title":"Evaluating the Performance and Robustness of LLMs in Materials Science Q&A and Property Predictions","created":"2024-09-22","cited_by_count":9,"area":null},{"id":"2410.11672","title":"Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answers","created":"2024-10-15","cited_by_count":9,"area":null},{"id":"2311.16466","title":"The Adoption and Efficacy of Large Language Models: Evidence From Consumer Complaints in the Financial Industry","created":"2023-11-28","cited_by_count":8,"area":null},{"id":"2411.02018","title":"Shortcut Learning in In-Context Learning: A Survey","created":"2024-11-04","cited_by_count":8,"area":null},{"id":"2101.00160","title":"How Do Your Biomedical Named Entity Recognition Models Generalize to Novel Entities?","created":"2021-01-01","cited_by_count":7,"area":null},{"id":"2102.06793","title":"Unanswerable Questions about Images and Texts","created":"2021-01-25","cited_by_count":7,"area":null},{"id":"2103.13942","title":"Visual Grounding Strategies for Text-Only Natural Language Processing","created":"2021-03-25","cited_by_count":7,"area":null},{"id":"2207.00982","title":"Linguistically inspired roadmap for building biologically reliable protein language models","created":"2022-07-03","cited_by_count":7,"area":null},{"id":"2209.08799","title":"Probing Spurious Correlations in Popular Event-Based Rumor Detection Benchmarks","created":"2022-09-19","cited_by_count":7,"area":null},{"id":"2310.05450","title":"Empower Nested Boolean Logic via Self-Supervised Curriculum Learning","created":"2023-10-09","cited_by_count":7,"area":"lr"},{"id":"2310.13191","title":"Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models","created":"2023-10-19","cited_by_count":7,"area":null},{"id":"2404.12145","title":"From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2409.12060","title":"PARAPHRASUS : A Comprehensive Benchmark for Evaluating Paraphrase Detection Models","created":"2024-09-18","cited_by_count":7,"area":null},{"id":"2105.14668","title":"On the Interplay Between Fine-tuning and Composition in Transformers","created":"2021-05-31","cited_by_count":6,"area":null},{"id":"2201.11115","title":"CsFEVER and CTKFacts: Acquiring Czech data for fact verification","created":"2022-01-26","cited_by_count":6,"area":null},{"id":"2208.08010","title":"ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2302.11978","title":"Does Deep Learning Learn to Abstract? A Systematic Probing Framework","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2305.08495","title":"Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks","created":"2023-05-15","cited_by_count":6,"area":null}],"next_cursor":"100"}