{"total":109,"rows":[{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876,"area":null},{"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":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2402.04614","title":"Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models","created":"2024-02-07","cited_by_count":105,"area":null},{"id":"2110.05006","title":"Pre-trained Language Models in Biomedical Domain: A Systematic Survey","created":"2021-10-11","cited_by_count":87,"area":null},{"id":"2305.13673","title":"Physics of Language Models: Part 1, Learning Hierarchical Language Structures","created":"2023-05-23","cited_by_count":83,"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":"2203.01054","title":"A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges","created":"2022-03-02","cited_by_count":61,"area":null},{"id":"2303.08117","title":"Do Transformers Parse while Predicting the Masked Word?","created":"2023-03-14","cited_by_count":48,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"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":"2104.04986","title":"Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa","created":"2021-04-11","cited_by_count":41,"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":"2311.03533","title":"Quantifying Uncertainty in Natural Language Explanations of Large Language Models","created":"2023-11-06","cited_by_count":32,"area":null},{"id":"2206.14017","title":"Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing","created":"2022-06-28","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":"2109.10540","title":"Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing","created":"2021-09-22","cited_by_count":28,"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":"2104.05904","title":"DirectProbe: Studying Representations without Classifiers","created":"2021-04-13","cited_by_count":25,"area":null},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"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":"2109.04740","title":"How Does Fine-tuning Affect the Geometry of Embedding Space: A Case Study on Isotropy","created":"2021-09-10","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":"2411.15102","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","created":"2024-11-22","cited_by_count":23,"area":null},{"id":"2208.03903","title":"Semantic Enhanced Text-to-SQL Parsing via Iteratively Learning Schema Linking Graph","created":"2022-08-08","cited_by_count":22,"area":null},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2204.13874","title":"OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision","created":"2022-04-29","cited_by_count":20,"area":null},{"id":"2107.00967","title":"R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling","created":"2021-07-02","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":"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":"2204.07359","title":"Text Revision by On-the-Fly Representation Optimization","created":"2022-04-15","cited_by_count":17,"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":"2306.01220","title":"Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2408.04532","title":"How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression","created":"2024-08-08","cited_by_count":14,"area":null},{"id":"2203.09627","title":"On the Importance of Data Size in Probing Fine-tuned Models","created":"2022-03-17","cited_by_count":12,"area":null},{"id":"2502.17204","title":"Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following","created":"2025-02-24","cited_by_count":12,"area":null},{"id":"2105.13665","title":"Domain-Adaptive Pretraining Methods for Dialogue Understanding","created":"2021-05-28","cited_by_count":11,"area":null},{"id":"2109.02403","title":"Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction","created":"2021-09-06","cited_by_count":11,"area":null},{"id":"2305.18213","title":"Gaussian Process Probes (GPP) for Uncertainty-Aware Probing","created":"2023-05-29","cited_by_count":11,"area":null},{"id":"2104.07058","title":"Predicting Discourse Trees from Transformer-based Neural Summarizers","created":"2021-04-14","cited_by_count":10,"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":"2112.07874","title":"Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling","created":"2021-12-15","cited_by_count":10,"area":null},{"id":"2109.11491","title":"Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords","created":"2021-09-23","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":"2502.10927","title":"The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training","created":"2025-02-15","cited_by_count":9,"area":null},{"id":"2409.14759","title":"VLM's Eye Examination: Instruct and Inspect Visual Competency of Vision Language Models","created":"2024-09-23","cited_by_count":8,"area":"lr"},{"id":"2103.01819","title":"The Rediscovery Hypothesis: Language Models Need to Meet Linguistics","created":"2021-03-02","cited_by_count":7,"area":null},{"id":"2206.01512","title":"Latent Topology Induction for Understanding Contextualized Representations","created":"2022-06-03","cited_by_count":7,"area":null},{"id":"2210.04382","title":"Parameter-Efficient Tuning with Special Token Adaptation","created":"2022-10-10","cited_by_count":7,"area":null},{"id":"2306.00645","title":"Contextual Distortion Reveals Constituency: Masked Language Models are Implicit Parsers","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2504.08001","title":"Linguistic Interpretability of Transformer-based Language Models: a systematic review","created":"2025-04-09","cited_by_count":7,"area":"mechinterp"},{"id":"2506.21812","title":"Towards Transparent AI: A Survey on Explainable Large Language Models","created":"2025-06-26","cited_by_count":7,"area":null},{"id":"2204.04289","title":"Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Models","created":"2022-04-08","cited_by_count":6,"area":null},{"id":"2305.10786","title":"Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings","created":"2023-05-18","cited_by_count":6,"area":null},{"id":"2305.18350","title":"Towards Open-World Product Attribute Mining: A Lightly-Supervised Approach","created":"2023-05-26","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":"2405.20404","title":"JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2410.13073","title":"PromptExp: Multi-granularity Prompt Explanation of Large Language Models","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2503.06048","title":"Constructions are Revealed in Word Distributions","created":"2025-03-08","cited_by_count":6,"area":null},{"id":"2202.09792","title":"Hierarchical Interpretation of Neural Text Classification","created":"2022-02-20","cited_by_count":5,"area":null},{"id":"2310.16654","title":"ChatGPT is a Potential Zero-Shot Dependency Parser","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2310.17936","title":"Transformers as Graph-to-Graph Models","created":"2023-10-27","cited_by_count":5,"area":null},{"id":"2406.02335","title":"Probing the Category of Verbal Aspect in Transformer Language Models","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2503.11248","title":"Reasoning-Grounded Natural Language Explanations for Language Models","created":"2025-03-14","cited_by_count":5,"area":"lr"},{"id":"2211.16031","title":"Syntactic Substitutability as Unsupervised Dependency Syntax","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2308.04712","title":"Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive Learning","created":"2023-08-09","cited_by_count":4,"area":null},{"id":"2108.13602","title":"How Does Adversarial Fine-Tuning Benefit BERT?","created":"2021-08-31","cited_by_count":3,"area":null},{"id":"2210.07519","title":"Can Language Representation Models Think in Bets?","created":"2022-10-14","cited_by_count":3,"area":"lr"},{"id":"2210.12302","title":"What do Large Language Models Learn beyond Language?","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2306.11943","title":"Towards Understanding What Code Language Models Learned","created":"2023-06-20","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":"2404.02650","title":"Towards detecting unanticipated bias in Large Language Models","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2408.11252","title":"Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2509.21631","title":"Towards Transparent AI: A Survey on Explainable Language Models","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2109.02572","title":"Enhancing Natural Language Representation with Large-Scale Out-of-Domain Commonsense","created":"2021-09-06","cited_by_count":2,"area":null},{"id":"2209.00820","title":"Structural Bias for Aspect Sentiment Triplet Extraction","created":"2022-09-02","cited_by_count":2,"area":null},{"id":"2210.01258","title":"Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes","created":"2022-10-03","cited_by_count":2,"area":"lr"},{"id":"2210.13002","title":"An Empirical Revisiting of Linguistic Knowledge Fusion in Language Understanding Tasks","created":"2022-10-24","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":"2404.12059","title":"Unsupervised Parsing by Searching for Frequent Word Sequences among Sentences with Equivalent Predicate-Argument Structures","created":"2024-04-18","cited_by_count":2,"area":null},{"id":"2510.17256","title":"Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations","created":"2025-10-20","cited_by_count":2,"area":"mechinterp"},{"id":"2603.02792","title":"From Heuristic Selection to Automated Algorithm Design: LLMs Benefit from Strong Priors","created":"2026-03-03","cited_by_count":2,"area":null},{"id":"2110.15712","title":"Analysing the Effect of Masking Length Distribution of MLM: An Evaluation Framework and Case Study on Chinese MRC Datasets","created":"2021-09-29","cited_by_count":1,"area":null},{"id":"2203.10315","title":"Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging","created":"2022-03-19","cited_by_count":1,"area":null},{"id":"2207.10849","title":"ASR Error Detection via Audio-Transcript entailment","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2211.00479","title":"Revisiting the Practical Effectiveness of Constituency Parse Extraction from Pre-trained Language Models","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2308.02193","title":"Explaining Relation Classification Models with Semantic Extents","created":"2023-08-04","cited_by_count":1,"area":null},{"id":"2310.16261","title":"The Distributional Hypothesis Does Not Fully Explain the Benefits of Masked Language Model Pretraining","created":"2023-10-25","cited_by_count":1,"area":null},{"id":"2312.17349","title":"Language Model as an Annotator: Unsupervised Context-aware Quality Phrase Generation","created":"2023-12-28","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},{"id":"2404.15877","title":"Effective Unsupervised Constrained Text Generation based on Perturbed Masking","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2505.12507","title":"Towards Structurally Explainable Machine-Generated Text Detection: A Graph-Perspective Framework","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2510.01652","title":"Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention","created":"2025-10-02","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":"2603.00696","title":"DRIV-EX: Counterfactual Explanations for Driving LLMs","created":"2026-02-28","cited_by_count":1,"area":"lr"},{"id":"2105.14850","title":"Cascaded Head-colliding Attention","created":"2021-05-31","cited_by_count":0,"area":null}],"next_cursor":"100"}