{"list":"other","total":70,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"2402.00159","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","created":"2024-01-31","cited_by_count":483},{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337},{"id":"2307.10088","title":"Android in the Wild: A Large-Scale Dataset for Android Device Control","created":"2023-07-19","cited_by_count":319},{"id":"2305.13534","title":"How Language Model Hallucinations Can Snowball","created":"2023-05-22","cited_by_count":311},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"2306.00297","title":"Transformers learn to implement preconditioned gradient descent for in-context learning","created":"2023-06-01","cited_by_count":279},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"2011.14878","title":"Explaining by Removing: A Unified Framework for Model Explanation","created":"2020-11-21","cited_by_count":218},{"id":"1907.07355","title":"Probing Neural Network Comprehension of Natural Language Arguments","created":"2019-07-17","cited_by_count":214},{"id":"2206.04624","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","created":"2022-06-09","cited_by_count":202},{"id":"1506.01066","title":"Visualizing and Understanding Neural Models in NLP","created":"2015-06-02","cited_by_count":200},{"id":"2308.03958","title":"Simple synthetic data reduces sycophancy in large language models","created":"2023-08-07","cited_by_count":187},{"id":"2309.13638","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","created":"2023-09-24","cited_by_count":178},{"id":"2307.03576","title":"One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention","created":"2023-07-07","cited_by_count":170},{"id":"2308.10168","title":"Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?","created":"2023-08-20","cited_by_count":168},{"id":"2412.05467","title":"The BrowserGym Ecosystem for Web Agent Research","created":"2024-12-06","cited_by_count":161},{"id":"2202.01602","title":"The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":159},{"id":"2110.07139","title":"Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer","created":"2021-10-14","cited_by_count":158},{"id":"2402.17553","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","created":"2024-02-27","cited_by_count":157},{"id":"2307.11019","title":"Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation","created":"2023-07-20","cited_by_count":147},{"id":"2204.07931","title":"On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?","created":"2022-04-17","cited_by_count":138},{"id":"2007.06778","title":"An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models","created":"2020-07-14","cited_by_count":134},{"id":"2402.14735","title":"How Transformers Learn Causal Structure with Gradient Descent","created":"2024-02-22","cited_by_count":118},{"id":"2311.14648","title":"Calibrated Language Models Must Hallucinate","created":"2023-11-24","cited_by_count":115},{"id":"2005.00115","title":"Learning to Faithfully Rationalize by Construction","created":"2020-04-30","cited_by_count":113},{"id":"2402.07945","title":"ScreenAgent: A Vision Language Model-driven Computer Control Agent","created":"2024-02-09","cited_by_count":102},{"id":"1912.09818","title":"When Explanations Lie: Why Many Modified BP Attributions Fail","created":"2019-12-20","cited_by_count":92},{"id":"2303.04245","title":"How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding","created":"2023-03-07","cited_by_count":86},{"id":"2004.14602","title":"Look at the First Sentence: Position Bias in Question Answering","created":"2020-04-30","cited_by_count":84},{"id":"2103.06922","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models","created":"2021-03-11","cited_by_count":78},{"id":"2212.11870","title":"Impossibility Theorems for Feature Attribution","created":"2022-12-22","cited_by_count":78},{"id":"2302.13942","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","created":"2023-02-27","cited_by_count":78},{"id":"2409.05746","title":"LLMs Will Always Hallucinate, and We Need to Live With This","created":"2024-09-09","cited_by_count":78},{"id":"1902.02302","title":"Neural Network Attributions: A Causal Perspective","created":"2019-02-06","cited_by_count":77},{"id":"2305.17256","title":"Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning","created":"2023-05-26","cited_by_count":69},{"id":"2305.15853","title":"Sequential Integrated Gradients: a simple but effective method for explaining language models","created":"2023-05-25","cited_by_count":52},{"id":"2412.06538","title":"Understanding Factual Recall in Transformers via Associative Memories","created":"2024-12-09","cited_by_count":51},{"id":"2409.10559","title":"Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers","created":"2024-09-09","cited_by_count":50},{"id":"2108.13654","title":"Discretized Integrated Gradients for Explaining Language Models","created":"2021-08-31","cited_by_count":46},{"id":"2301.12971","title":"Quantifying Context Mixing in Transformers","created":"2023-01-30","cited_by_count":43},{"id":"2203.16747","title":"How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis","created":"2022-03-31","cited_by_count":42},{"id":"2204.05514","title":"A Comparative Study of Faithfulness Metrics for Model Interpretability Methods","created":"2022-04-12","cited_by_count":39},{"id":"2501.08292","title":"HALoGEN: Fantastic LLM Hallucinations and Where to Find Them","created":"2025-01-14","cited_by_count":34},{"id":"2403.19851","title":"Localizing Paragraph Memorization in Language Models","created":"2024-03-28","cited_by_count":31},{"id":"2109.06387","title":"Rationales for Sequential Predictions","created":"2021-09-14","cited_by_count":26},{"id":"2407.08039","title":"Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models","created":"2024-07-10","cited_by_count":25},{"id":"2410.13343","title":"Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models","created":"2024-10-17","cited_by_count":25},{"id":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18},{"id":"2305.10496","title":"Incorporating Attribution Importance for Improving Faithfulness Metrics","created":"2023-05-17","cited_by_count":14},{"id":"2402.09259","title":"SyntaxShap: Syntax-aware Explainability Method for Text Generation","created":"2024-02-14","cited_by_count":11},{"id":"2403.07955","title":"Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery","created":"2024-03-12","cited_by_count":8},{"id":"2312.07553","title":"Hijacking Context in Large Multi-modal Models","created":"2023-12-07","cited_by_count":6},{"id":"2402.08479","title":"Plausible Extractive Rationalization through Semi-Supervised Entailment Signal","created":"2024-02-13","cited_by_count":6}],"next_cursor":null}