{"total":78,"rows":[{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2106.06087","title":"Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models","created":"2021-06-10","cited_by_count":131,"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":"2303.04245","title":"How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding","created":"2023-03-07","cited_by_count":86,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"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":"2309.15098","title":"Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models","created":"2023-09-26","cited_by_count":67,"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":"2202.06840","title":"What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code","created":"2022-02-14","cited_by_count":50,"area":null},{"id":"2109.04825","title":"Artificial Text Detection via Examining the Topology of Attention Maps","created":"2021-09-10","cited_by_count":49,"area":null},{"id":"2205.03286","title":"GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers","created":"2022-05-06","cited_by_count":44,"area":null},{"id":"2301.12971","title":"Quantifying Context Mixing in Transformers","created":"2023-01-30","cited_by_count":43,"area":null},{"id":"2204.11073","title":"Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps","created":"2022-04-23","cited_by_count":42,"area":null},{"id":"2104.07012","title":"Sparse Attention with Linear Units","created":"2021-04-14","cited_by_count":41,"area":null},{"id":"2310.19956","title":"The Impact of Depth on Compositional Generalization in Transformer Language Models","created":"2023-10-30","cited_by_count":38,"area":null},{"id":"2305.11408","title":"AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation","created":"2023-05-19","cited_by_count":35,"area":null},{"id":"2212.07850","title":"Attention as a Guide for Simultaneous Speech Translation","created":"2022-12-15","cited_by_count":32,"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":"2408.07144","title":"Language Models as Models of Language","created":"2024-08-13","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":"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":"2407.14662","title":"Relational Composition in Neural Networks: A Survey and Call to Action","created":"2024-07-19","cited_by_count":23,"area":null},{"id":"2101.10927","title":"Attention Can Reflect Syntactic Structure (If You Let It)","created":"2021-01-26","cited_by_count":22,"area":null},{"id":"2105.13868","title":"Learning Relation Alignment for Calibrated Cross-modal Retrieval","created":"2021-05-28","cited_by_count":21,"area":null},{"id":"2211.03495","title":"How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers","created":"2022-11-07","cited_by_count":21,"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":"2101.04547","title":"Of Non-Linearity and Commutativity in BERT","created":"2021-01-12","cited_by_count":16,"area":null},{"id":"2108.13759","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","created":"2021-08-31","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":"2104.09400","title":"Probing for Bridging Inference in Transformer Language Models","created":"2021-04-19","cited_by_count":14,"area":null},{"id":"2502.11856","title":"LLMs as a synthesis between symbolic and distributed approaches to language","created":"2025-02-17","cited_by_count":13,"area":null},{"id":"2101.00371","title":"On-the-Fly Attention Modulation for Neural Generation","created":"2021-01-02","cited_by_count":12,"area":null},{"id":"2502.05390","title":"Learning Task Representations from In-Context Learning","created":"2025-02-08","cited_by_count":11,"area":null},{"id":"2104.08685","title":"Linguistic Dependencies and Statistical Dependence","created":"2021-04-18","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":"2207.08466","title":"What does Transformer learn about source code?","created":"2022-07-18","cited_by_count":9,"area":null},{"id":"2310.18696","title":"Probing LLMs for Joint Encoding of Linguistic Categories","created":"2023-10-28","cited_by_count":9,"area":null},{"id":"2110.08130","title":"Breaking Down Multilingual Machine Translation","created":"2021-10-15","cited_by_count":8,"area":null},{"id":"2306.06205","title":"Morphosyntactic probing of multilingual BERT models","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2407.17406","title":"Dependency Transformer Grammars: Integrating Dependency Structures into Transformer Language Models","created":"2024-07-24","cited_by_count":8,"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":"2110.08887","title":"Schr\\\"odinger's Tree -- On Syntax and Neural Language Models","created":"2021-10-17","cited_by_count":6,"area":null},{"id":"2403.03028","title":"Word Importance Explains How Prompts Affect Language Model Outputs","created":"2024-03-05","cited_by_count":6,"area":null},{"id":"2406.16563","title":"Are there identifiable structural parts in the sentence embedding whole?","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2504.04335","title":"Hallucinated Span Detection with Multi-View Attention Features","created":"2025-04-06","cited_by_count":6,"area":null},{"id":"2102.07926","title":"Have Attention Heads in BERT Learned Constituency Grammar?","created":"2021-02-16","cited_by_count":5,"area":null},{"id":"2106.01580","title":"The Limitations of Limited Context for Constituency Parsing","created":"2021-06-03","cited_by_count":5,"area":null},{"id":"2211.06420","title":"The Architectural Bottleneck Principle","created":"2022-11-11","cited_by_count":5,"area":null},{"id":"2405.16727","title":"Disentangling and Integrating Relational and Sensory Information in Transformer Architectures","created":"2024-05-26","cited_by_count":5,"area":null},{"id":"2204.10176","title":"Probing Script Knowledge from Pre-Trained Models","created":"2022-04-16","cited_by_count":4,"area":null},{"id":"2211.16031","title":"Syntactic Substitutability as Unsupervised Dependency Syntax","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2311.15211","title":"Probabilistic Transformer: A Probabilistic Dependency Model for Contextual Word Representation","created":"2023-11-26","cited_by_count":4,"area":null},{"id":"2412.05353","title":"Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models","created":"2024-12-06","cited_by_count":4,"area":null},{"id":"2104.06835","title":"Enhancing Word-Level Semantic Representation via Dependency Structure for Expressive Text-to-Speech Synthesis","created":"2021-04-14","cited_by_count":3,"area":null},{"id":"2211.06229","title":"Improving word mover's distance by leveraging self-attention matrix","created":"2022-11-11","cited_by_count":3,"area":null},{"id":"2403.11747","title":"Embedded Named Entity Recognition using Probing Classifiers","created":"2024-03-18","cited_by_count":3,"area":null},{"id":"2403.16447","title":"A Study on How Attention Scores in the BERT Model are Aware of Lexical Categories in Syntactic and Semantic Tasks on the GLUE Benchmark","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2211.00106","title":"Data-Efficient Cross-Lingual Transfer with Language-Specific Subnetworks","created":"2022-10-31","cited_by_count":2,"area":null},{"id":"2212.10792","title":"Reconstruction Probing","created":"2022-12-21","cited_by_count":2,"area":null},{"id":"2310.15905","title":"Is Probing All You Need? Indicator Tasks as an Alternative to Probing Embedding Spaces","created":"2023-10-24","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":"2209.03557","title":"Does Attention Mechanism Possess the Feature of Human Reading? A Perspective of Sentiment Classification Task","created":"2022-09-08","cited_by_count":1,"area":null},{"id":"2402.06492","title":"Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings","created":"2024-02-09","cited_by_count":1,"area":null},{"id":"2410.13396","title":"Linguistically Grounded Analysis of Language Models using Shapley Head Values","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2508.14685","title":"SSA: Improving Performance With a Better Scoring Function","created":"2025-08-20","cited_by_count":1,"area":null},{"id":"2510.16439","title":"FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution","created":"2025-10-18","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":"2206.04806","title":"Syntactic Inductive Biases for Deep Learning Methods","created":"2022-06-08","cited_by_count":0,"area":null},{"id":"2206.04980","title":"Unsupervised and Few-shot Parsing from Pretrained Language Models","created":"2022-06-10","cited_by_count":0,"area":null},{"id":"2305.13403","title":"GATology for Linguistics: What Syntactic Dependencies It Knows","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2310.11363","title":"Disentangling the Linguistic Competence of Privacy-Preserving BERT","created":"2023-10-17","cited_by_count":0,"area":null},{"id":"2311.00268","title":"Syntactic Inductive Bias in Transformer Language Models: Especially Helpful for Low-Resource Languages?","created":"2023-11-01","cited_by_count":0,"area":null},{"id":"2312.14966","title":"Dynamic Syntax Mapping: A New Approach to Unsupervised Syntax Parsing","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2404.01992","title":"Dissecting Paraphrases: The Impact of Prompt Syntax and supplementary Information on Knowledge Retrieval from Pretrained Language Models","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2503.02255","title":"AxBERT: An Interpretable Chinese Spelling Correction Method Driven by Associative Knowledge Network","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2609.07779","title":"CodeTD: Topology of Attention Detects Hallucinations in Code LLMs","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}