{"list":"other","total":53,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"1907.11932","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","created":"2019-07-27","cited_by_count":671},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"1804.07998","title":"Generating Natural Language Adversarial Examples","created":"2018-04-21","cited_by_count":424},{"id":"1904.01130","title":"PAWS: Paraphrase Adversaries from Word Scrambling","created":"2019-04-01","cited_by_count":402},{"id":"1801.04354","title":"Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers","created":"2018-01-13","cited_by_count":345},{"id":"1711.02173","title":"Synthetic and Natural Noise Both Break Neural Machine Translation","created":"2017-11-06","cited_by_count":306},{"id":"2011.10369","title":"ONION: A Simple and Effective Defense Against Textual Backdoor Attacks","created":"2020-11-20","cited_by_count":263},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237},{"id":"1905.12457","title":"A backdoor attack against LSTM-based text classification systems","created":"2019-05-29","cited_by_count":227},{"id":"2105.12400","title":"Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger","created":"2021-05-26","cited_by_count":222},{"id":"1909.00986","title":"Certified Robustness to Adversarial Word Substitutions","created":"2019-09-03","cited_by_count":168},{"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":"1803.04585","title":"Categorizing Variants of Goodhart's Law","created":"2018-03-13","cited_by_count":149},{"id":"2010.07100","title":"Re-evaluating Evaluation in Text Summarization","created":"2020-10-14","cited_by_count":145},{"id":"1906.05416","title":"Synthetic QA Corpora Generation with Roundtrip Consistency","created":"2019-06-12","cited_by_count":143},{"id":"2008.05723","title":"Contextual Diversity for Active Learning","created":"2020-08-13","cited_by_count":139},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107},{"id":"1903.11508","title":"Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems","created":"2019-03-27","cited_by_count":101},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97},{"id":"1909.01492","title":"Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation","created":"2019-09-03","cited_by_count":88},{"id":"2212.03363","title":"Few-Shot Preference Learning for Human-in-the-Loop RL","created":"2022-12-06","cited_by_count":87},{"id":"2004.10157","title":"Logic-Guided Data Augmentation and Regularization for Consistent Question Answering","created":"2020-04-21","cited_by_count":78},{"id":"2104.09061","title":"Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection","created":"2021-04-19","cited_by_count":76},{"id":"1910.03065","title":"Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations","created":"2019-10-07","cited_by_count":71},{"id":"2004.05887","title":"Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples","created":"2020-04-13","cited_by_count":54},{"id":"2103.10013","title":"Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!","created":"2021-03-18","cited_by_count":53},{"id":"2205.01287","title":"SemAttack: Natural Textual Attacks via Different Semantic Spaces","created":"2022-05-03","cited_by_count":42},{"id":"1909.06723","title":"Natural Language Adversarial Defense through Synonym Encoding","created":"2019-09-15","cited_by_count":40},{"id":"2211.11875","title":"Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference","created":"2022-11-21","cited_by_count":40},{"id":"2202.08479","title":"On the Evaluation Metrics for Paraphrase Generation","created":"2022-02-17","cited_by_count":32},{"id":"1905.03177","title":"Does Data Augmentation Lead to Positive Margin?","created":"2019-05-08","cited_by_count":18},{"id":"2011.10492","title":"A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger's Adversarial Attacks","created":"2020-11-20","cited_by_count":15},{"id":"1906.08942","title":"Be Consistent! Improving Procedural Text Comprehension using Label Consistency","created":"2019-06-21","cited_by_count":10},{"id":"2302.02023","title":"TextShield: Beyond Successfully Detecting Adversarial Sentences in Text Classification","created":"2023-02-03","cited_by_count":8},{"id":"2104.08401","title":"Enriching a Model's Notion of Belief using a Persistent Memory","created":"2021-04-16","cited_by_count":4}],"next_cursor":null}