{"total":115,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291,"area":null},{"id":"2103.11790","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","created":"2021-03-08","cited_by_count":178,"area":null},{"id":"2309.01809","title":"Are Emergent Abilities in Large Language Models just In-Context Learning?","created":"2023-09-04","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":"2105.11115","title":"Self-Attention Networks Can Process Bounded Hierarchical Languages","created":"2021-05-24","cited_by_count":105,"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":"2203.17247","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","created":"2022-03-30","cited_by_count":53,"area":null},{"id":"2109.07152","title":"Incorporating Residual and Normalization Layers into Analysis of Masked Language Models","created":"2021-09-15","cited_by_count":51,"area":null},{"id":"2305.03210","title":"AttentionViz: A Global View of Transformer Attention","created":"2023-05-04","cited_by_count":50,"area":null},{"id":"2301.12971","title":"Quantifying Context Mixing in Transformers","created":"2023-01-30","cited_by_count":43,"area":null},{"id":"2109.06939","title":"The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders","created":"2021-09-14","cited_by_count":32,"area":null},{"id":"2110.08182","title":"The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of Color","created":"2021-10-15","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":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2109.04953","title":"Does Pretraining for Summarization Require Knowledge Transfer?","created":"2021-09-10","cited_by_count":30,"area":null},{"id":"2312.01429","title":"Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars","created":"2023-12-03","cited_by_count":30,"area":null},{"id":"2104.01477","title":"Exploring the Role of BERT Token Representations to Explain Sentence Probing Results","created":"2021-04-03","cited_by_count":29,"area":null},{"id":"2109.10540","title":"Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing","created":"2021-09-22","cited_by_count":28,"area":null},{"id":"2204.13346","title":"UniTE: Unified Translation Evaluation","created":"2022-04-28","cited_by_count":28,"area":null},{"id":"2104.12874","title":"Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attention","created":"2021-04-26","cited_by_count":27,"area":null},{"id":"2203.05922","title":"Visualizing and Understanding Patch Interactions in Vision Transformer","created":"2022-03-11","cited_by_count":26,"area":null},{"id":"2404.16367","title":"Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers","created":"2024-04-25","cited_by_count":24,"area":null},{"id":"2106.01950","title":"The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models","created":"2021-06-03","cited_by_count":23,"area":null},{"id":"2206.04727","title":"STNDT: Modeling Neural Population Activity with a Spatiotemporal Transformer","created":"2022-06-09","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":"2301.11462","title":"How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech","created":"2023-01-26","cited_by_count":22,"area":null},{"id":"2402.14700","title":"Unveiling Linguistic Regions in Large Language Models","created":"2024-02-22","cited_by_count":22,"area":null},{"id":"2109.03160","title":"How much pretraining data do language models need to learn syntax?","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2110.07310","title":"Solving Aspect Category Sentiment Analysis as a Text Generation Task","created":"2021-10-14","cited_by_count":21,"area":null},{"id":"2209.14389","title":"Downstream Datasets Make Surprisingly Good Pretraining Corpora","created":"2022-09-28","cited_by_count":20,"area":null},{"id":"2109.12036","title":"Transformers Generalize Linearly","created":"2021-09-24","cited_by_count":19,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2205.09630","title":"Acceptability Judgements via Examining the Topology of Attention Maps","created":"2022-05-19","cited_by_count":19,"area":null},{"id":"2210.08471","title":"Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion","created":"2022-10-16","cited_by_count":18,"area":null},{"id":"2305.09144","title":"Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models","created":"2023-05-16","cited_by_count":18,"area":null},{"id":"2305.16784","title":"Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization","created":"2023-05-26","cited_by_count":17,"area":null},{"id":"2101.04547","title":"Of Non-Linearity and Commutativity in BERT","created":"2021-01-12","cited_by_count":16,"area":null},{"id":"2101.09115","title":"The heads hypothesis: A unifying statistical approach towards understanding multi-headed attention in BERT","created":"2021-01-22","cited_by_count":15,"area":null},{"id":"2208.08176","title":"Visual Comparison of Language Model Adaptation","created":"2022-08-17","cited_by_count":14,"area":null},{"id":"2309.00254","title":"Why do universal adversarial attacks work on large language models?: Geometry might be the answer","created":"2023-09-01","cited_by_count":14,"area":null},{"id":"2410.11627","title":"Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5","created":"2024-10-15","cited_by_count":14,"area":null},{"id":"2101.10726","title":"Regulatory Compliance through Doc2Doc Information Retrieval: A case study in EU/UK legislation where text similarity has limitations","created":"2021-01-26","cited_by_count":13,"area":null},{"id":"2310.09925","title":"Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers","created":"2023-10-15","cited_by_count":13,"area":null},{"id":"2311.04900","title":"How Abstract Is Linguistic Generalization in Large Language Models? Experiments with Argument Structure","created":"2023-11-08","cited_by_count":13,"area":null},{"id":"2106.01317","title":"Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization","created":"2021-06-02","cited_by_count":11,"area":null},{"id":"2502.05390","title":"Learning Task Representations from In-Context Learning","created":"2025-02-08","cited_by_count":11,"area":null},{"id":"2107.13955","title":"Local Structure Matters Most: Perturbation Study in NLU","created":"2021-07-29","cited_by_count":10,"area":null},{"id":"2109.14017","title":"Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations","created":"2021-09-28","cited_by_count":10,"area":null},{"id":"2406.03707","title":"What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions","created":"2024-06-06","cited_by_count":10,"area":null},{"id":"2407.16891","title":"Cultural Value Differences of LLMs: Prompt, Language, and Model Size","created":"2024-06-17","cited_by_count":10,"area":null},{"id":"2411.07474","title":"Controlled Evaluation of Syntactic Knowledge in Multilingual Language Models","created":"2024-11-12","cited_by_count":10,"area":null},{"id":"2203.17081","title":"Interpretation of Black Box NLP Models: A Survey","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2207.08466","title":"What does Transformer learn about source code?","created":"2022-07-18","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":"2301.04704","title":"SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings","created":"2023-01-11","cited_by_count":9,"area":null},{"id":"2203.13397","title":"GPT-D: Inducing Dementia-related Linguistic Anomalies by Deliberate Degradation of Artificial Neural Language Models","created":"2022-03-25","cited_by_count":8,"area":null},{"id":"2409.15827","title":"Unveiling Language Competence Neurons: A Psycholinguistic Approach to Model Interpretability","created":"2024-09-24","cited_by_count":8,"area":null},{"id":"2103.13799","title":"Bertinho: Galician BERT Representations","created":"2021-03-25","cited_by_count":7,"area":null},{"id":"2109.05748","title":"GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks","created":"2021-09-13","cited_by_count":7,"area":null},{"id":"2205.03759","title":"Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information","created":"2022-05-08","cited_by_count":7,"area":null},{"id":"2312.14226","title":"Deep de Finetti: Recovering Topic Distributions from Large Language Models","created":"2023-12-21","cited_by_count":7,"area":null},{"id":"2406.10584","title":"Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models","created":"2024-06-15","cited_by_count":7,"area":null},{"id":"2505.08546","title":"Are We Paying Attention to Her? Investigating Gender Disambiguation and Attention in Machine Translation","created":"2025-05-13","cited_by_count":7,"area":null},{"id":"2101.11492","title":"On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations","created":"2021-01-27","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":"2310.14422","title":"Large Language Models are biased to overestimate profoundness","created":"2023-10-22","cited_by_count":6,"area":null},{"id":"2311.07996","title":"How Well Do Text Embedding Models Understand Syntax?","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2308.05219","title":"Decoding Layer Saliency in Language Transformers","created":"2023-08-09","cited_by_count":5,"area":null},{"id":"2503.18751","title":"Construction Identification and Disambiguation Using BERT: A Case Study of NPN","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2103.14973","title":"Explaining the Road Not Taken","created":"2021-03-27","cited_by_count":3,"area":null},{"id":"2106.07349","title":"Using Integrated Gradients and Constituency Parse Trees to explain Linguistic Acceptability learnt by BERT","created":"2021-06-01","cited_by_count":3,"area":null},{"id":"2111.11331","title":"Vector Space Semantics for Lambek Calculus with Soft Subexponentials","created":"2021-11-22","cited_by_count":3,"area":null},{"id":"2203.01063","title":"Discontinuous Constituency and BERT: A Case Study of Dutch","created":"2022-03-02","cited_by_count":3,"area":null},{"id":"2205.11987","title":"Word-order typology in Multilingual BERT: A case study in subordinate-clause detection","created":"2022-05-24","cited_by_count":3,"area":null},{"id":"2206.02440","title":"A computational psycholinguistic evaluation of the syntactic abilities of Galician BERT models at the interface of dependency resolution and training time","created":"2022-06-06","cited_by_count":3,"area":null},{"id":"2207.06960","title":"Forming Trees with Treeformers","created":"2022-07-14","cited_by_count":3,"area":null},{"id":"2209.11128","title":"Learning Interpretable Latent Dialogue Actions With Less Supervision","created":"2022-09-22","cited_by_count":3,"area":null},{"id":"2210.12206","title":"Probing with Noise: Unpicking the Warp and Weft of Embeddings","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2210.12302","title":"What do Large Language Models Learn beyond Language?","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2403.02009","title":"Topic Aware Probing: From Sentence Length Prediction to Idiom Identification how reliant are Neural Language Models on Topic?","created":"2024-03-04","cited_by_count":3,"area":null},{"id":"2106.03181","title":"Transient Chaos in BERT","created":"2021-06-06","cited_by_count":2,"area":null},{"id":"2108.10127","title":"Legal Search in Case Law and Statute Law","created":"2021-08-23","cited_by_count":2,"area":null},{"id":"2109.05361","title":"COMBO: State-of-the-Art Morphosyntactic Analysis","created":"2021-09-11","cited_by_count":2,"area":null},{"id":"2204.04596","title":"Parameter-Efficient Tuning by Manipulating Hidden States of Pretrained Language Models For Classification Tasks","created":"2022-04-10","cited_by_count":2,"area":null},{"id":"2302.08822","title":"False perspectives on human language: why statistics needs linguistics","created":"2023-02-17","cited_by_count":2,"area":null},{"id":"2310.17271","title":"Understanding the Role of Input Token Characters in Language Models: How Does Information Loss Affect Performance?","created":"2023-10-26","cited_by_count":2,"area":null},{"id":"2310.18930","title":"Retrofitting Light-weight Language Models for Emotions using Supervised Contrastive Learning","created":"2023-10-29","cited_by_count":2,"area":null},{"id":"2403.02173","title":"What has LeBenchmark Learnt about French Syntax?","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2403.18183","title":"Can AI Models Appreciate Document Aesthetics? An Exploration of Legibility and Layout Quality in Relation to Prediction Confidence","created":"2024-03-27","cited_by_count":2,"area":null},{"id":"2502.00344","title":"FinchGPT: a Transformer based language model for birdsong analysis","created":"2025-02-01","cited_by_count":2,"area":null},{"id":"2601.03798","title":"Where meaning lives: Layer-wise accessibility of psycholinguistic features in encoder and decoder language models","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2103.00854","title":"Vy\\=akarana: A Colorless Green Benchmark for Syntactic Evaluation in Indic Languages","created":"2021-03-01","cited_by_count":1,"area":null},{"id":"2210.06928","title":"Sentence Ambiguity, Grammaticality and Complexity Probes","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2303.03457","title":"Spelling convention sensitivity in neural language models","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2303.07585","title":"Input-length-shortening and text generation via attention values","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2306.14182","title":"Switch-BERT: Learning to Model Multimodal Interactions by Switching Attention and Input","created":"2023-06-25","cited_by_count":1,"area":null},{"id":"2312.08027","title":"Helping Language Models Learn More: Multi-dimensional Task Prompt for Few-shot Tuning","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2404.14270","title":"What do Transformers Know about Government?","created":"2024-04-22","cited_by_count":1,"area":null}],"next_cursor":"100"}