{"total":398,"rows":[{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876,"area":null},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"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":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291,"area":null},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211,"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":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178,"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":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"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":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2103.06678","title":"The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models","created":"2021-03-11","cited_by_count":119,"area":null},{"id":"2108.13888","title":"Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning","created":"2021-08-31","cited_by_count":113,"area":null},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111,"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":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108,"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":"2208.07998","title":"What Artificial Neural Networks Can Tell Us About Human Language Acquisition","created":"2022-08-17","cited_by_count":99,"area":null},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","cited_by_count":97,"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":"2106.09226","title":"Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning","created":"2021-06-17","cited_by_count":82,"area":null},{"id":"2104.05832","title":"SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning","created":"2021-04-12","cited_by_count":77,"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":"2104.07885","title":"Probing Across Time: What Does RoBERTa Know and When?","created":"2021-04-16","cited_by_count":73,"area":null},{"id":"2102.13249","title":"Chess as a Testbed for Language Model State Tracking","created":"2021-02-26","cited_by_count":72,"area":null},{"id":"2112.02690","title":"Open Vocabulary Electroencephalography-To-Text Decoding and Zero-shot Sentiment Classification","created":"2021-12-05","cited_by_count":67,"area":null},{"id":"2210.12329","title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","created":"2022-10-22","cited_by_count":67,"area":null},{"id":"2402.16061","title":"How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study","created":"2024-02-25","cited_by_count":64,"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":"2204.08831","title":"Probing for the Usage of Grammatical Number","created":"2022-04-19","cited_by_count":59,"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":"2205.07237","title":"Discovering Latent Concepts Learned in BERT","created":"2022-05-15","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":"2101.11131","title":"CLiMP: A Benchmark for Chinese Language Model Evaluation","created":"2021-01-26","cited_by_count":46,"area":null},{"id":"2102.04110","title":"Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration","created":"2021-02-08","cited_by_count":44,"area":null},{"id":"2109.14989","title":"Structural Persistence in Language Models: Priming as a Window into Abstract Language Representations","created":"2021-09-30","cited_by_count":44,"area":null},{"id":"2304.06248","title":"LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model","created":"2023-04-13","cited_by_count":43,"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":"2105.07109","title":"The Low-Dimensional Linear Geometry of Contextualized Word Representations","created":"2021-05-15","cited_by_count":40,"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":"2303.09859","title":"Trained on 100 million words and still in shape: BERT meets British National Corpus","created":"2023-03-17","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":"2104.05824","title":"Evaluating Saliency Methods for Neural Language Models","created":"2021-04-12","cited_by_count":37,"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":"2109.06096","title":"The Grammar-Learning Trajectories of Neural Language Models","created":"2021-09-13","cited_by_count":36,"area":null},{"id":"2401.01862","title":"A Vision Check-up for Language Models","created":"2024-01-03","cited_by_count":36,"area":null},{"id":"2409.14381","title":"Investigating Layer Importance in Large Language Models","created":"2024-09-22","cited_by_count":36,"area":null},{"id":"2210.13181","title":"The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative","created":"2022-10-24","cited_by_count":35,"area":null},{"id":"2106.08556","title":"Coreference-Aware Dialogue Summarization","created":"2021-06-16","cited_by_count":34,"area":null},{"id":"2310.16570","title":"Give Me the Facts! A Survey on Factual Knowledge Probing in Pre-trained Language Models","created":"2023-10-25","cited_by_count":32,"area":null},{"id":"2401.06416","title":"Mission: Impossible Language Models","created":"2024-01-12","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":"2109.08406","title":"Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers","created":"2021-09-17","cited_by_count":30,"area":null},{"id":"2203.14139","title":"Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages","created":"2022-03-26","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":"2305.19249","title":"Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models","created":"2023-05-30","cited_by_count":29,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","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":"2109.12393","title":"Sorting through the noise: Testing robustness of information processing in pre-trained language models","created":"2021-09-25","cited_by_count":27,"area":null},{"id":"2206.12279","title":"AnyMorph: Learning Transferable Polices By Inferring Agent Morphology","created":"2022-06-17","cited_by_count":27,"area":null},{"id":"2202.08975","title":"Probing Pretrained Models of Source Code","created":"2022-02-16","cited_by_count":26,"area":null},{"id":"2210.14102","title":"Exploring Mode Connectivity for Pre-trained Language Models","created":"2022-10-25","cited_by_count":26,"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":"2109.10246","title":"Does Vision-and-Language Pretraining Improve Lexical Grounding?","created":"2021-09-21","cited_by_count":25,"area":null},{"id":"2502.07586","title":"We Can't Understand AI Using our Existing Vocabulary","created":"2025-02-11","cited_by_count":25,"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":"2211.09748","title":"Probing for Incremental Parse States in Autoregressive Language Models","created":"2022-11-17","cited_by_count":24,"area":null},{"id":"2403.17299","title":"Decoding Probing: Revealing Internal Linguistic Structures in Neural Language Models using Minimal Pairs","created":"2024-03-26","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":"2407.08582","title":"On the Universal Truthfulness Hyperplane Inside LLMs","created":"2024-07-11","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":"2204.00212","title":"Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems","created":"2022-04-01","cited_by_count":23,"area":null},{"id":"2208.10244","title":"Unit Testing for Concepts in Neural Networks","created":"2022-07-28","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":"2102.10934","title":"Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks","created":"2021-02-22","cited_by_count":22,"area":null},{"id":"2109.03853","title":"A Bayesian Framework for Information-Theoretic Probing","created":"2021-09-08","cited_by_count":22,"area":null},{"id":"2303.05759","title":"An Overview on Language Models: Recent Developments and Outlook","created":"2023-03-10","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":"2407.13934","title":"Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models","created":"2024-06-01","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":"2211.04079","title":"COPEN: Probing Conceptual Knowledge in Pre-trained Language Models","created":"2022-11-08","cited_by_count":21,"area":null},{"id":"2305.05968","title":"Investigating Forgetting in Pre-Trained Representations Through Continual Learning","created":"2023-05-10","cited_by_count":21,"area":null},{"id":"2404.12444","title":"mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?","created":"2024-04-18","cited_by_count":21,"area":null},{"id":"2104.04515","title":"Connecting Attributions and QA Model Behavior on Realistic Counterfactuals","created":"2021-04-09","cited_by_count":20,"area":null},{"id":"2109.10616","title":"Enriching and Controlling Global Semantics for Text Summarization","created":"2021-09-22","cited_by_count":20,"area":null},{"id":"2304.05216","title":"Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyond","created":"2023-04-11","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":"2106.07935","title":"BERT Embeddings for Automatic Readability Assessment","created":"2021-06-15","cited_by_count":19,"area":null},{"id":"2109.04947","title":"Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding","created":"2021-09-10","cited_by_count":19,"area":null},{"id":"2305.14057","title":"Can Language Models Understand Physical Concepts?","created":"2023-05-23","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":"2108.11696","title":"Rethinking Why Intermediate-Task Fine-Tuning Works","created":"2021-08-26","cited_by_count":18,"area":null},{"id":"2206.09355","title":"A Unified Understanding of Deep NLP Models for Text Classification","created":"2022-06-19","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":"2402.19465","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","created":"2024-02-29","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":"2306.12213","title":"Limits for Learning with Language Models","created":"2023-06-21","cited_by_count":17,"area":null}],"next_cursor":"100"}