{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"2104.06378","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","created":"2021-04-13","cited_by_count":388},{"id":"2204.02329","title":"Can language models learn from explanations in context?","created":"2022-04-05","cited_by_count":249},{"id":"2305.14160","title":"Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning","created":"2023-05-23","cited_by_count":236},{"id":"2201.08860","title":"GreaseLM: Graph REASoning Enhanced Language Models for Question Answering","created":"2022-01-21","cited_by_count":171},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"2009.13295","title":"A Diagnostic Study of Explainability Techniques for Text Classification","created":"2020-09-25","cited_by_count":159},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"2004.05773","title":"Generating Fact Checking Explanations","created":"2020-04-13","cited_by_count":132},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130},{"id":"1904.02342","title":"Text Generation from Knowledge Graphs with Graph Transformers","created":"2019-04-04","cited_by_count":122},{"id":"2007.08426","title":"Investigating Pretrained Language Models for Graph-to-Text Generation","created":"2020-07-16","cited_by_count":117},{"id":"2402.13950","title":"Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning","created":"2024-02-21","cited_by_count":110},{"id":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107},{"id":"2305.01879","title":"SCOTT: Self-Consistent Chain-of-Thought Distillation","created":"2023-05-03","cited_by_count":105},{"id":"2005.12116","title":"NILE : Natural Language Inference with Faithful Natural Language Explanations","created":"2020-05-25","cited_by_count":96},{"id":"2105.05727","title":"BertGCN: Transductive Text Classification by Combining GCN and BERT","created":"2021-05-12","cited_by_count":74},{"id":"2311.07466","title":"On Measuring Faithfulness or Self-consistency of Natural Language Explanations","created":"2023-11-13","cited_by_count":73},{"id":"2211.01562","title":"PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales","created":"2022-11-03","cited_by_count":56},{"id":"1908.09022","title":"Neural data-to-text generation: A comparison between pipeline and end-to-end architectures","created":"2019-08-23","cited_by_count":51},{"id":"2305.11426","title":"Post Hoc Explanations of Language Models Can Improve Language Models","created":"2023-05-19","cited_by_count":50},{"id":"2007.00236","title":"SemEval-2020 Task 4: Commonsense Validation and Explanation","created":"2020-07-01","cited_by_count":42},{"id":"2209.04889","title":"Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech","created":"2022-09-11","cited_by_count":25},{"id":"2106.13876","title":"Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations","created":"2021-06-25","cited_by_count":24},{"id":"2111.12951","title":"Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift","created":"2021-11-25","cited_by_count":22},{"id":"2309.13391","title":"D-Separation for Causal Self-Explanation","created":"2023-09-23","cited_by_count":21},{"id":"2409.10790","title":"Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering","created":"2024-09-16","cited_by_count":17},{"id":"2307.14712","title":"Evaluating Generative Models for Graph-to-Text Generation","created":"2023-07-27","cited_by_count":16},{"id":"2112.06924","title":"Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing","created":"2021-12-13","cited_by_count":15},{"id":"2312.04103","title":"Enhancing the Rationale-Input Alignment for Self-explaining Rationalization","created":"2023-12-07","cited_by_count":15},{"id":"2107.01671","title":"Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory","created":"2021-07-04","cited_by_count":14},{"id":"2305.13599","title":"Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint","created":"2023-05-23","cited_by_count":14},{"id":"2406.03953","title":"Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech","created":"2024-06-06","cited_by_count":11},{"id":"2410.06003","title":"Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization","created":"2024-10-08","cited_by_count":11},{"id":"2402.12038","title":"Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations","created":"2024-02-19","cited_by_count":8},{"id":"2406.15085","title":"Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework","created":"2024-06-21","cited_by_count":5}],"next_cursor":null}