{"total":209,"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":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966,"area":null},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841,"area":null},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449,"area":null},{"id":"2104.06378","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","created":"2021-04-13","cited_by_count":388,"area":null},{"id":"2102.01017","title":"Measuring and Improving Consistency in Pretrained Language Models","created":"2021-02-01","cited_by_count":364,"area":null},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337,"area":null},{"id":"2310.07641","title":"Evaluating Large Language Models at Evaluating Instruction Following","created":"2023-10-11","cited_by_count":302,"area":null},{"id":"2211.05110","title":"Large Language Models with Controllable Working Memory","created":"2022-11-09","cited_by_count":169,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2205.10782","title":"Instruction Induction: From Few Examples to Natural Language Task Descriptions","created":"2022-05-22","cited_by_count":152,"area":null},{"id":"2109.06157","title":"SituatedQA: Incorporating Extra-Linguistic Contexts into QA","created":"2021-09-13","cited_by_count":145,"area":null},{"id":"2102.00894","title":"Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models","created":"2021-02-01","cited_by_count":132,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120,"area":null},{"id":"2312.09085","title":"The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation","created":"2023-12-14","cited_by_count":109,"area":null},{"id":"2106.09231","title":"Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases","created":"2021-06-17","cited_by_count":107,"area":null},{"id":"2311.00059","title":"The Generative AI Paradox: \"What It Can Create, It May Not Understand\"","created":"2023-10-31","cited_by_count":98,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2306.08189","title":"Language models are not naysayers: An analysis of language models on negation benchmarks","created":"2023-06-14","cited_by_count":74,"area":null},{"id":"2105.03519","title":"Understanding by Understanding Not: Modeling Negation in Language Models","created":"2021-05-07","cited_by_count":73,"area":null},{"id":"2308.06374","title":"Large Language Models and Knowledge Graphs: Opportunities and Challenges","created":"2023-08-11","cited_by_count":71,"area":null},{"id":"2202.06335","title":"ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification","created":"2022-02-13","cited_by_count":66,"area":null},{"id":"2101.00403","title":"Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words","created":"2021-01-02","cited_by_count":63,"area":null},{"id":"2109.14723","title":"BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief","created":"2021-09-29","cited_by_count":57,"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":"2311.16153","title":"Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications","created":"2023-11-07","cited_by_count":54,"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":"2109.14989","title":"Structural Persistence in Language Models: Priming as a Window into Abstract Language Representations","created":"2021-09-30","cited_by_count":44,"area":null},{"id":"2202.09381","title":"Synthetic Disinformation Attacks on Automated Fact Verification Systems","created":"2022-02-18","cited_by_count":44,"area":null},{"id":"2106.14282","title":"A Closer Look at How Fine-tuning Changes BERT","created":"2021-06-27","cited_by_count":42,"area":null},{"id":"2106.02902","title":"BERTnesia: Investigating the capture and forgetting of knowledge in BERT","created":"2021-06-05","cited_by_count":40,"area":null},{"id":"2211.00295","title":"CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation","created":"2022-11-01","cited_by_count":39,"area":null},{"id":"2201.12438","title":"Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey","created":"2022-01-28","cited_by_count":38,"area":null},{"id":"2210.12217","title":"Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning","created":"2022-10-21","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":"2303.06273","title":"Consistency Analysis of ChatGPT","created":"2023-03-11","cited_by_count":37,"area":null},{"id":"2209.07065","title":"CommunityLM: Probing Partisan Worldviews from Language Models","created":"2022-09-15","cited_by_count":36,"area":null},{"id":"2210.13181","title":"The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative","created":"2022-10-24","cited_by_count":35,"area":null},{"id":"2211.07733","title":"Speaking Multiple Languages Affects the Moral Bias of Language Models","created":"2022-11-14","cited_by_count":34,"area":null},{"id":"2110.08455","title":"Knowledge Enhanced Pretrained Language Models: A Compreshensive Survey","created":"2021-10-16","cited_by_count":33,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2305.05976","title":"Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge","created":"2023-05-10","cited_by_count":32,"area":null},{"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":"2303.10475","title":"Large Language Model Instruction Following: A Survey of Progresses and Challenges","created":"2023-03-18","cited_by_count":31,"area":null},{"id":"2409.13724","title":"Logically Consistent Language Models via Neuro-Symbolic Integration","created":"2024-09-09","cited_by_count":30,"area":null},{"id":"2502.21228","title":"ECLeKTic: a Novel Challenge Set for Evaluation of Cross-Lingual Knowledge Transfer","created":"2025-02-28","cited_by_count":29,"area":null},{"id":"2109.12393","title":"Sorting through the noise: Testing robustness of information processing in pre-trained language models","created":"2021-09-25","cited_by_count":27,"area":null},{"id":"2310.11958","title":"Emptying the Ocean with a Spoon: Should We Edit Models?","created":"2023-10-18","cited_by_count":27,"area":null},{"id":"2104.06511","title":"\"I'm Not Mad\": Commonsense Implications of Negation and Contradiction","created":"2021-04-13","cited_by_count":26,"area":null},{"id":"2203.15867","title":"Image Retrieval from Contextual Descriptions","created":"2022-03-29","cited_by_count":26,"area":null},{"id":"2104.05904","title":"DirectProbe: Studying Representations without Classifiers","created":"2021-04-13","cited_by_count":25,"area":null},{"id":"2109.13006","title":"RuleBert: Teaching Soft Rules to Pre-trained Language Models","created":"2021-09-24","cited_by_count":25,"area":null},{"id":"2210.03256","title":"Not another Negation Benchmark: The NaN-NLI Test Suite for Sub-clausal Negation","created":"2022-10-06","cited_by_count":25,"area":null},{"id":"2403.14859","title":"Log Probabilities Are a Reliable Estimate of Semantic Plausibility in Base and Instruction-Tuned Language Models","created":"2024-03-21","cited_by_count":24,"area":null},{"id":"2203.07653","title":"Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness","created":"2022-03-15","cited_by_count":23,"area":null},{"id":"2303.07616","title":"The Life Cycle of Knowledge in Big Language Models: A Survey","created":"2023-03-14","cited_by_count":23,"area":null},{"id":"2206.08005","title":"Evaluating Self-Supervised Learning for Molecular Graph Embeddings","created":"2022-06-16","cited_by_count":22,"area":null},{"id":"2212.08979","title":"Language model acceptability judgements are not always robust to context","created":"2022-12-18","cited_by_count":22,"area":null},{"id":"2302.12297","title":"Dynamic Benchmarking of Masked Language Models on Temporal Concept Drift with Multiple Views","created":"2023-02-23","cited_by_count":21,"area":null},{"id":"2310.08256","title":"Impact of Co-occurrence on Factual Knowledge of Large Language Models","created":"2023-10-12","cited_by_count":19,"area":null},{"id":"2209.15093","title":"Unpacking Large Language Models with Conceptual Consistency","created":"2022-09-29","cited_by_count":18,"area":null},{"id":"2310.15941","title":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models","created":"2023-10-24","cited_by_count":18,"area":null},{"id":"2210.12574","title":"The Curious Case of Absolute Position Embeddings","created":"2022-10-23","cited_by_count":17,"area":null},{"id":"2306.12213","title":"Limits for Learning with Language Models","created":"2023-06-21","cited_by_count":17,"area":null},{"id":"2307.13989","title":"This is not correct! Negation-aware Evaluation of Language Generation Systems","created":"2023-07-26","cited_by_count":17,"area":null},{"id":"2205.00132","title":"Learn to Understand Negation in Video Retrieval","created":"2022-04-30","cited_by_count":16,"area":null},{"id":"2103.13033","title":"Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2","created":"2021-03-24","cited_by_count":15,"area":null},{"id":"2203.11552","title":"Factual Consistency of Multilingual Pretrained Language Models","created":"2022-03-22","cited_by_count":15,"area":null},{"id":"2210.01963","title":"COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models","created":"2022-10-05","cited_by_count":15,"area":null},{"id":"2305.14250","title":"Language Models with Rationality","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2305.19589","title":"SLABERT Talk Pretty One Day: Modeling Second Language Acquisition with BERT","created":"2023-05-31","cited_by_count":15,"area":null},{"id":"2406.05494","title":"Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation","created":"2024-06-08","cited_by_count":15,"area":null},{"id":"2410.04241","title":"Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations","created":"2024-10-05","cited_by_count":15,"area":null},{"id":"2412.16100","title":"Logical Consistency of Large Language Models in Fact-checking","created":"2024-12-20","cited_by_count":15,"area":null},{"id":"2502.14258","title":"Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information","created":"2025-02-20","cited_by_count":15,"area":null},{"id":"2407.11015","title":"Does ChatGPT Have a Mind?","created":"2024-06-27","cited_by_count":14,"area":null},{"id":"2108.06665","title":"Accurate, yet inconsistent? Consistency Analysis on Language Understanding Models","created":"2021-08-15","cited_by_count":13,"area":null},{"id":"2209.07430","title":"Machine Reading, Fast and Slow: When Do Models \"Understand\" Language?","created":"2022-09-15","cited_by_count":13,"area":null},{"id":"2309.05936","title":"Do PLMs Know and Understand Ontological Knowledge?","created":"2023-09-12","cited_by_count":13,"area":null},{"id":"2310.09820","title":"Assessing the Reliability of Large Language Model Knowledge","created":"2023-10-15","cited_by_count":13,"area":null},{"id":"2403.09963","title":"Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction","created":"2024-03-15","cited_by_count":13,"area":null},{"id":"2510.24963","title":"Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale","created":"2025-10-28","cited_by_count":13,"area":null},{"id":"2204.03084","title":"Knowledge Infused Decoding","created":"2022-04-06","cited_by_count":12,"area":null},{"id":"2211.10997","title":"Embracing Ambiguity: Improving Similarity-oriented Tasks with Contextual Synonym Knowledge","created":"2022-11-20","cited_by_count":12,"area":null},{"id":"2305.05050","title":"ANALOGICAL -- A Novel Benchmark for Long Text Analogy Evaluation in Large Language Models","created":"2023-05-08","cited_by_count":12,"area":null},{"id":"2305.16797","title":"Calibration of Transformer-based Models for Identifying Stress and Depression in Social Media","created":"2023-05-26","cited_by_count":12,"area":null},{"id":"2305.17311","title":"Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models","created":"2023-05-27","cited_by_count":12,"area":null},{"id":"2309.07251","title":"In-Contextual Gender Bias Suppression for Large Language Models","created":"2023-09-13","cited_by_count":12,"area":null},{"id":"2102.05628","title":"On the Regularity of Attention","created":"2021-02-10","cited_by_count":11,"area":null},{"id":"2104.07094","title":"Static Embeddings as Efficient Knowledge Bases?","created":"2021-04-14","cited_by_count":11,"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":"2502.01609","title":"Adaptive Distraction: Probing LLM Contextual Robustness with Automated Tree Search","created":"2025-02-03","cited_by_count":10,"area":null},{"id":"2102.05331","title":"Language Models for Lexical Inference in Context","created":"2021-02-10","cited_by_count":9,"area":null},{"id":"2110.07165","title":"Semantically Distributed Robust Optimization for Vision-and-Language Inference","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2209.07836","title":"Negation, Coordination, and Quantifiers in Contextualized Language Models","created":"2022-09-16","cited_by_count":9,"area":null},{"id":"2312.00960","title":"The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models","created":"2023-12-01","cited_by_count":9,"area":null},{"id":"2406.12277","title":"What Matters in Memorizing and Recalling Facts? Multifaceted Benchmarks for Knowledge Probing in Language Models","created":"2024-06-18","cited_by_count":9,"area":null}],"next_cursor":"100"}