{"total":36,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293,"area":null},{"id":"2310.03668","title":"GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction","created":"2023-10-05","cited_by_count":119,"area":null},{"id":"2312.16337","title":"Task Contamination: Language Models May Not Be Few-Shot Anymore","created":"2023-12-26","cited_by_count":99,"area":null},{"id":"2305.02105","title":"GPT-RE: In-context Learning for Relation Extraction using Large Language Models","created":"2023-05-03","cited_by_count":62,"area":null},{"id":"2404.18923","title":"Holmes: A Benchmark to Assess the Linguistic Competence of Language Models","created":"2024-04-29","cited_by_count":26,"area":null},{"id":"2401.14556","title":"Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labeling","created":"2024-01-25","cited_by_count":24,"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":"2305.00948","title":"Large Linguistic Models: Investigating LLMs' metalinguistic abilities","created":"2023-05-01","cited_by_count":18,"area":null},{"id":"2305.14489","title":"Are Large Language Models Robust Coreference Resolvers?","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2410.09013","title":"The Impact of Visual Information in Chinese Characters: Evaluating Large Models' Ability to Recognize and Utilize Radicals","created":"2024-10-11","cited_by_count":10,"area":null},{"id":"2405.20588","title":"DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models","created":"2024-05-31","cited_by_count":9,"area":null},{"id":"2412.12276","title":"Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective","created":"2024-12-16","cited_by_count":9,"area":null},{"id":"2401.16589","title":"ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks","created":"2024-01-29","cited_by_count":7,"area":null},{"id":"2506.06950","title":"What Makes a Good Natural Language Prompt?","created":"2025-06-07","cited_by_count":7,"area":null},{"id":"2310.12794","title":"Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalization","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2503.19260","title":"Linguistic Blind Spots of Large Language Models","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2305.14775","title":"Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2311.07484","title":"Psychometric Predictive Power of Large Language Models","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2401.06877","title":"Promptly Predicting Structures: The Return of Inference","created":"2024-01-12","cited_by_count":4,"area":null},{"id":"2406.14099","title":"Let Guidelines Guide You: A Prescriptive Guideline-Centered Data Annotation Methodology","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2504.17311","title":"FLUKE: A Linguistically-Driven and Task-Agnostic Framework for Robustness Evaluation","created":"2025-04-24","cited_by_count":3,"area":null},{"id":"2506.01205","title":"Trick or Neat: Adversarial Ambiguity and Language Model Evaluation","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2402.18397","title":"Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models","created":"2024-02-28","cited_by_count":2,"area":null},{"id":"2403.03861","title":"Designing Informative Metrics for Few-Shot Example Selection","created":"2024-03-06","cited_by_count":2,"area":null},{"id":"2502.20866","title":"Better Benchmarking LLMs for Zero-Shot Dependency Parsing","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2506.01237","title":"Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2310.13092","title":"Do Language Models Learn about Legal Entity Types during Pretraining?","created":"2023-10-19","cited_by_count":1,"area":null},{"id":"2504.02395","title":"The quasi-semantic competence of LLMs: a case study on the part-whole relation","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2601.19926","title":"The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2412.20043","title":"STAYKATE: Hybrid In-Context Example Selection Combining Representativeness Sampling and Retrieval-based Approach -- A Case Study on Science Domains","created":"2024-12-28","cited_by_count":0,"area":null},{"id":"2503.12667","title":"Plausibility Vaccine: Injecting LLM Knowledge for Event Plausibility","created":"2025-03-16","cited_by_count":0,"area":null},{"id":"2506.21222","title":"Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2602.20300","title":"What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.16718","title":"Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.02171","title":"Do Lexical and Contextual Coreference Resolution Systems Degrade Differently under Mention Noise? An Empirical Study on Scientific Software Mentions","created":"2026-04-02","cited_by_count":0,"area":null}],"next_cursor":null}