{"list":"other","total":64,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"2309.03882","title":"Large Language Models Are Not Robust Multiple Choice Selectors","created":"2023-09-07","cited_by_count":486},{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369},{"id":"1902.10178","title":"Unmasking Clever Hans Predictors and Assessing What Machines Really Learn","created":"2019-02-26","cited_by_count":365},{"id":"2404.02060","title":"Long-context LLMs Struggle with Long In-context Learning","created":"2024-04-02","cited_by_count":286},{"id":"2104.08315","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","created":"2021-04-16","cited_by_count":263},{"id":"2308.11483","title":"Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions","created":"2023-08-22","cited_by_count":263},{"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":"2205.10343","title":"Towards Understanding Grokking: An Effective Theory of Representation Learning","created":"2022-05-20","cited_by_count":230},{"id":"2212.04037","title":"Demystifying Prompts in Language Models via Perplexity Estimation","created":"2022-12-08","cited_by_count":216},{"id":"1907.07355","title":"Probing Neural Network Comprehension of Natural Language Arguments","created":"2019-07-17","cited_by_count":214},{"id":"2311.01964","title":"Don't Make Your LLM an Evaluation Benchmark Cheater","created":"2023-11-03","cited_by_count":194},{"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":"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":"2305.09731","title":"What In-Context Learning \"Learns\" In-Context: Disentangling Task Recognition and Task Learning","created":"2023-05-16","cited_by_count":152},{"id":"2310.11207","title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","created":"2023-10-17","cited_by_count":90},{"id":"2305.19148","title":"Mitigating Label Biases for In-context Learning","created":"2023-05-28","cited_by_count":89},{"id":"2004.14602","title":"Look at the First Sentence: Position Bias in Question Answering","created":"2020-04-30","cited_by_count":84},{"id":"2012.01300","title":"Learning from others' mistakes: Avoiding dataset biases without modeling them","created":"2020-12-02","cited_by_count":83},{"id":"2402.12483","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","created":"2024-02-19","cited_by_count":71},{"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":"2205.10183","title":"Prototypical Calibration for Few-shot Learning of Language Models","created":"2022-05-20","cited_by_count":58},{"id":"2307.12375","title":"In-Context Learning Learns Label Relationships but Is Not Conventional Learning","created":"2023-07-23","cited_by_count":51},{"id":"2305.13299","title":"Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations","created":"2023-05-22","cited_by_count":49},{"id":"2311.08648","title":"Explore Spurious Correlations at the Concept Level in Language Models for Text Classification","created":"2023-11-15","cited_by_count":48},{"id":"2004.03490","title":"What do Models Learn from Question Answering Datasets?","created":"2020-04-07","cited_by_count":45},{"id":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40},{"id":"2005.04732","title":"Towards Robustifying NLI Models Against Lexical Dataset Biases","created":"2020-05-10","cited_by_count":34},{"id":"2404.16966","title":"Examining the robustness of LLM evaluation to the distributional assumptions of benchmarks","created":"2024-04-25","cited_by_count":31},{"id":"2405.20612","title":"UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation","created":"2024-05-31","cited_by_count":31},{"id":"2205.03784","title":"Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis","created":"2022-05-08","cited_by_count":30},{"id":"2403.02738","title":"Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment","created":"2024-03-05","cited_by_count":30},{"id":"2105.05912","title":"MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation","created":"2021-05-12","cited_by_count":27},{"id":"2311.09702","title":"Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?","created":"2023-11-16","cited_by_count":26},{"id":"2311.09627","title":"Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination","created":"2023-11-16","cited_by_count":23},{"id":"2402.01155","title":"CABINET: Content Relevance based Noise Reduction for Table Question Answering","created":"2024-02-02","cited_by_count":23},{"id":"2402.10688","title":"Towards Uncovering How Large Language Model Works: An Explainability Perspective","created":"2024-02-16","cited_by_count":22},{"id":"2310.10266","title":"Generative Calibration for In-context Learning","created":"2023-10-16","cited_by_count":20},{"id":"2406.03628","title":"Synthetic Oversampling: Theory and A Practical Approach Using LLMs to Address Data Imbalance","created":"2024-06-05","cited_by_count":17},{"id":"2409.02257","title":"MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs","created":"2024-09-03","cited_by_count":16},{"id":"2312.16549","title":"How Robust are LLMs to In-Context Majority Label Bias?","created":"2023-12-27","cited_by_count":14},{"id":"2406.13764","title":"Can LLMs Reason in the Wild with Programs?","created":"2024-06-19","cited_by_count":13},{"id":"2407.18328","title":"Unveiling Scoring Processes: Dissecting the Differences between LLMs and Human Graders in Automatic Scoring","created":"2024-07-04","cited_by_count":13},{"id":"2410.01288","title":"Mitigating Copy Bias in In-Context Learning through Neuron Pruning","created":"2024-10-02","cited_by_count":11},{"id":"2310.18360","title":"Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers","created":"2023-10-24","cited_by_count":10},{"id":"2409.17455","title":"Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models","created":"2024-09-26","cited_by_count":10},{"id":"2310.05163","title":"An Investigation of LLMs' Inefficacy in Understanding Converse Relations","created":"2023-10-08","cited_by_count":9},{"id":"2403.09488","title":"Rectifying Demonstration Shortcut in In-Context Learning","created":"2024-03-14","cited_by_count":9},{"id":"2401.09615","title":"Learning Shortcuts: On the Misleading Promise of NLU in Language Models","created":"2024-01-17","cited_by_count":4}],"next_cursor":null}