{"total":126,"rows":[{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675,"area":null},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"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":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2103.15049","title":"HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval","created":"2021-03-28","cited_by_count":87,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2307.15780","title":"LLM-Rec: Personalized Recommendation via Prompting Large Language Models","created":"2023-07-24","cited_by_count":77,"area":null},{"id":"2109.09234","title":"Conditional probing: measuring usable information beyond a baseline","created":"2021-09-19","cited_by_count":62,"area":null},{"id":"2410.13640","title":"Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation","created":"2024-10-17","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":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56,"area":null},{"id":"2104.03869","title":"Probing BERT in Hyperbolic Spaces","created":"2021-04-08","cited_by_count":50,"area":null},{"id":"2310.00935","title":"Resolving Knowledge Conflicts in Large Language Models","created":"2023-10-02","cited_by_count":50,"area":null},{"id":"2209.01307","title":"TransPolymer: a Transformer-based language model for polymer property predictions","created":"2022-09-03","cited_by_count":43,"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":"2406.00048","title":"Towards a theory of how the structure of language is acquired by deep neural networks","created":"2024-05-28","cited_by_count":39,"area":null},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2507.11412","title":"Seq vs Seq: An Open Suite of Paired Encoders and Decoders","created":"2025-07-15","cited_by_count":38,"area":null},{"id":"2108.11308","title":"What do pre-trained code models know about code?","created":"2021-08-25","cited_by_count":36,"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":"2310.13002","title":"Are Large Language Models Geospatially Knowledgeable?","created":"2023-10-09","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":"2108.01661","title":"Grounding Representation Similarity with Statistical Testing","created":"2021-08-03","cited_by_count":29,"area":null},{"id":"2210.13050","title":"Structural generalization is hard for sequence-to-sequence models","created":"2022-10-24","cited_by_count":24,"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":"2602.07488","title":"Deriving Neural Scaling Laws from the statistics of natural language","created":"2026-02-07","cited_by_count":23,"area":null},{"id":"2310.03686","title":"DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers","created":"2023-10-05","cited_by_count":22,"area":null},{"id":"2307.10246","title":"Deep Neural Networks and Brain Alignment: Brain Encoding and Decoding (Survey)","created":"2023-07-17","cited_by_count":21,"area":null},{"id":"2408.07539","title":"Cross-aware Early Fusion with Stage-divided Vision and Language Transformer Encoders for Referring Image Segmentation","created":"2024-08-14","cited_by_count":21,"area":null},{"id":"2209.00154","title":"Contextualized language models for semantic change detection: lessons learned","created":"2022-08-31","cited_by_count":20,"area":null},{"id":"2312.04333","title":"Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers","created":"2023-12-07","cited_by_count":20,"area":null},{"id":"2210.04710","title":"Empowering the Fact-checkers! Automatic Identification of Claim Spans on Twitter","created":"2022-10-10","cited_by_count":19,"area":null},{"id":"2104.05694","title":"On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies","created":"2021-04-12","cited_by_count":18,"area":null},{"id":"2105.12449","title":"LMMS Reloaded: Transformer-based Sense Embeddings for Disambiguation and Beyond","created":"2021-05-26","cited_by_count":17,"area":null},{"id":"2105.13471","title":"Inspecting the concept knowledge graph encoded by modern language models","created":"2021-05-27","cited_by_count":15,"area":null},{"id":"2109.07205","title":"A Relation-Oriented Clustering Method for Open Relation Extraction","created":"2021-09-15","cited_by_count":15,"area":null},{"id":"2209.07859","title":"Extracting Biomedical Factual Knowledge Using Pretrained Language Model and Electronic Health Record Context","created":"2022-08-26","cited_by_count":15,"area":null},{"id":"2310.02832","title":"Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness","created":"2023-10-04","cited_by_count":15,"area":null},{"id":"2104.06400","title":"Mediators in Determining what Processing BERT Performs First","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2204.06201","title":"Probing for Constituency Structure in Neural Language Models","created":"2022-04-13","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":"2402.11094","title":"Revisiting Word Embeddings in the LLM Era","created":"2024-02-16","cited_by_count":13,"area":null},{"id":"2404.03021","title":"Blessing or curse? A survey on the Impact of Generative AI on Fake News","created":"2024-04-03","cited_by_count":12,"area":null},{"id":"2101.11287","title":"Language Modelling as a Multi-Task Problem","created":"2021-01-27","cited_by_count":10,"area":null},{"id":"2107.00439","title":"What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis","created":"2021-07-01","cited_by_count":9,"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":"2308.03228","title":"Why Linguistics Will Thrive in the 21st Century: A Reply to Piantadosi (2023)","created":"2023-08-06","cited_by_count":9,"area":null},{"id":"2103.10133","title":"Evaluating Document Coherence Modelling","created":"2021-03-18","cited_by_count":8,"area":null},{"id":"2207.01736","title":"Probing via Prompting","created":"2022-07-04","cited_by_count":7,"area":null},{"id":"2409.19663","title":"Identifying Knowledge Editing Types in Large Language Models","created":"2024-09-29","cited_by_count":7,"area":null},{"id":"2102.02111","title":"Introduction to Neural Transfer Learning with Transformers for Social Science Text Analysis","created":"2021-02-03","cited_by_count":6,"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":"2109.07909","title":"Studying Fake News Spreading, Polarisation Dynamics, and Manipulation by Bots: a Tale of Networks and Language","created":"2021-09-13","cited_by_count":6,"area":null},{"id":"2309.14084","title":"Comprehensive Overview of Named Entity Recognition: Models, Domain-Specific Applications and Challenges","created":"2023-09-25","cited_by_count":6,"area":null},{"id":"2310.15372","title":"EpiK-Eval: Evaluation for Language Models as Epistemic Models","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2402.01375","title":"Dive into the Chasm: Probing the Gap between In- and Cross-Topic Generalization","created":"2024-02-02","cited_by_count":6,"area":null},{"id":"2411.05036","title":"From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2106.01060","title":"John praised Mary because he? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs","created":"2021-06-02","cited_by_count":5,"area":null},{"id":"2107.10413","title":"Theoretical foundations and limits of word embeddings: what types of meaning can they capture?","created":"2021-07-22","cited_by_count":5,"area":null},{"id":"2110.06920","title":"Semantics-aware Attention Improves Neural Machine Translation","created":"2021-10-13","cited_by_count":5,"area":null},{"id":"2305.04940","title":"The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification","created":"2023-05-08","cited_by_count":5,"area":null},{"id":"2508.03211","title":"Probing Syntax in Large Language Models: Successes and Remaining Challenges","created":"2025-08-05","cited_by_count":5,"area":null},{"id":"2602.06065","title":"Deep networks learn to parse uniform-depth context-free languages from local statistics","created":"2026-01-31","cited_by_count":5,"area":null},{"id":"2102.03596","title":"Does He Wink or Does He Nod? A Challenging Benchmark for Evaluating Word Understanding of Language Models","created":"2021-02-06","cited_by_count":4,"area":null},{"id":"2304.12706","title":"What does BERT learn about prosody?","created":"2023-04-25","cited_by_count":4,"area":null},{"id":"2406.18045","title":"PharmaGPT: Domain-Specific Large Language Models for Bio-Pharmaceutical and Chemistry","created":"2024-06-26","cited_by_count":4,"area":null},{"id":"2106.05365","title":"DESCGEN: A Distantly Supervised Dataset for Generating Abstractive Entity Descriptions","created":"2021-06-09","cited_by_count":3,"area":null},{"id":"2106.09589","title":"Classifying vaccine sentiment tweets by modelling domain-specific representation and commonsense knowledge into context-aware attentive GRU","created":"2021-06-17","cited_by_count":3,"area":null},{"id":"2106.13445","title":"A Picture May Be Worth a Hundred Words for Visual Question Answering","created":"2021-06-25","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":"2301.02458","title":"Topics as Entity Clusters: Entity-based Topics from Large Language Models and Graph Neural Networks","created":"2023-01-06","cited_by_count":3,"area":null},{"id":"2405.17799","title":"Exploring Activation Patterns of Parameters in Language Models","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2504.14107","title":"Signatures of human-like processing in Transformer forward passes","created":"2025-04-18","cited_by_count":3,"area":null},{"id":"2103.05434","title":"When is it permissible for artificial intelligence to lie? A trust-based approach","created":"2021-03-09","cited_by_count":2,"area":null},{"id":"2209.15197","title":"Evaluation of taxonomic and neural embedding methods for calculating semantic similarity","created":"2022-09-30","cited_by_count":2,"area":null},{"id":"2305.19689","title":"Assessing Word Importance Using Models Trained for Semantic Tasks","created":"2023-05-31","cited_by_count":2,"area":null},{"id":"2306.00103","title":"ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning","created":"2023-05-31","cited_by_count":2,"area":null},{"id":"2308.08625","title":"BIOptimus: Pre-training an Optimal Biomedical Language Model with Curriculum Learning for Named Entity Recognition","created":"2023-08-16","cited_by_count":2,"area":null},{"id":"2312.05092","title":"INSPECT: Intrinsic and Systematic Probing Evaluation for Code Transformers","created":"2023-12-08","cited_by_count":2,"area":null},{"id":"2410.04765","title":"Molecular topological deep learning for polymer property prediction","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2410.16165","title":"From Tokens to Materials: Leveraging Language Models for Scientific Discovery","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2504.08712","title":"Beyond Black-Box Predictions: Identifying Marginal Feature Effects in Tabular Transformer Networks","created":"2025-04-11","cited_by_count":2,"area":null},{"id":"2204.04793","title":"Fake news detection using parallel BERT deep neural networks","created":"2022-04-10","cited_by_count":1,"area":null},{"id":"2204.12710","title":"CREER: A Large-Scale Corpus for Relation Extraction and Entity Recognition","created":"2022-04-27","cited_by_count":1,"area":null},{"id":"2210.02526","title":"\"No, they did not\": Dialogue response dynamics in pre-trained language models","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2301.04347","title":"Counteracts: Testing Stereotypical Representation in Pre-trained Language Models","created":"2023-01-11","cited_by_count":1,"area":null},{"id":"2410.09349","title":"Inference and Verbalization Functions During In-Context Learning","created":"2024-10-12","cited_by_count":1,"area":null},{"id":"2410.13318","title":"Computational Approaches to Arabic-English Code-Switching","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2501.08281","title":"NEUROLOGIC: From Neural Representations to Interpretable Logic Rules","created":"2025-01-14","cited_by_count":1,"area":null},{"id":"2503.23534","title":"BiPVL-Seg: Bidirectional Progressive Vision-Language Fusion with Global-Local Alignment for Medical Image Segmentation","created":"2025-03-30","cited_by_count":1,"area":null},{"id":"2506.11096","title":"Assessing the Impact of Anisotropy in Neural Representations of Speech: A Case Study on Keyword Spotting","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2506.22516","title":"Can \"consciousness\" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysis","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2509.05254","title":"Uniform Information Density and Syntactic Reduction: Revisiting $\\textit{that}$-Mentioning in English Complement Clauses","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2511.00519","title":"Exploring and Mitigating Gender Bias in Encoder-Based Transformer Models","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2603.10130","title":"The Prediction-Measurement Gap: Toward Meaning Representations as Scientific Instruments","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2606.19668","title":"Code-Switching Reveals Language Anchoring in Multilingual LLMs","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2609.28784","title":"Script Choice in LLMs: Evidence for Late-Layer Commitment","created":"2026-09-23","cited_by_count":1,"area":null},{"id":"2103.16414","title":"Representing ELMo embeddings as two-dimensional text online","created":"2021-03-30","cited_by_count":0,"area":null},{"id":"2111.05937","title":"Recent Advances in Automated Question Answering In Biomedical Domain","created":"2021-11-10","cited_by_count":0,"area":null}],"next_cursor":"100"}