{"list":"other","total":80,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397},{"id":"1911.03891","title":"Social Bias Frames: Reasoning about Social and Power Implications of Language","created":"2019-11-10","cited_by_count":380},{"id":"2101.05783","title":"Persistent Anti-Muslim Bias in Large Language Models","created":"2021-01-14","cited_by_count":377},{"id":"2110.05719","title":"Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations","created":"2021-10-12","cited_by_count":314},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284},{"id":"2011.00620","title":"Social Chemistry 101: Learning to Reason about Social and Moral Norms","created":"2020-11-01","cited_by_count":255},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225},{"id":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181},{"id":"1908.06083","title":"Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack","created":"2019-08-17","cited_by_count":176},{"id":"1908.07898","title":"Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets","created":"2019-08-21","cited_by_count":175},{"id":"2010.07079","title":"Recipes for Safety in Open-domain Chatbots","created":"2020-10-14","cited_by_count":170},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169},{"id":"2010.03532","title":"What Can We Learn from Collective Human Opinions on Natural Language Inference Data?","created":"2020-10-07","cited_by_count":153},{"id":"1707.02633","title":"Controlling Linguistic Style Aspects in Neural Language Generation","created":"2017-07-09","cited_by_count":149},{"id":"2302.02676","title":"Chain of Hindsight Aligns Language Models with Feedback","created":"2023-02-06","cited_by_count":148},{"id":"2112.01640","title":"MultiVerS: Improving scientific claim verification with weak supervision and full-document context","created":"2021-12-02","cited_by_count":143},{"id":"2102.04130","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","created":"2021-02-08","cited_by_count":141},{"id":"2110.07574","title":"Can Machines Learn Morality? The Delphi Experiment","created":"2021-10-14","cited_by_count":141},{"id":"2209.07572","title":"Power to the People? Opportunities and Challenges for Participatory AI","created":"2022-09-15","cited_by_count":138},{"id":"2110.05699","title":"On Releasing Annotator-Level Labels and Information in Datasets","created":"2021-10-12","cited_by_count":126},{"id":"2202.02950","title":"Jury Learning: Integrating Dissenting Voices into Machine Learning Models","created":"2022-02-07","cited_by_count":118},{"id":"1901.05415","title":"Learning from Dialogue after Deployment: Feed Yourself, Chatbot!","created":"2019-01-16","cited_by_count":102},{"id":"2008.09094","title":"Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes","created":"2020-08-20","cited_by_count":101},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93},{"id":"2204.03021","title":"The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems","created":"2022-04-06","cited_by_count":93},{"id":"2210.01478","title":"When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment","created":"2022-10-04","cited_by_count":93},{"id":"1909.01214","title":"Better Rewards Yield Better Summaries: Learning to Summarise Without References","created":"2019-09-03","cited_by_count":77},{"id":"2104.14795","title":"Mitigating Political Bias in Language Models Through Reinforced Calibration","created":"2021-04-30","cited_by_count":73},{"id":"1707.07402","title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback","created":"2017-07-24","cited_by_count":72},{"id":"1805.10627","title":"Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning","created":"2018-05-27","cited_by_count":57},{"id":"1804.06512","title":"Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems","created":"2018-04-18","cited_by_count":53},{"id":"1909.00105","title":"Generating Personalized Recipes from Historical User Preferences","created":"2019-08-31","cited_by_count":53},{"id":"1610.05461","title":"Personalized Machine Translation: Preserving Original Author Traits","created":"2016-10-18","cited_by_count":47},{"id":"1611.09823","title":"Dialogue Learning With Human-In-The-Loop","created":"2016-11-29","cited_by_count":46},{"id":"2106.01465","title":"Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?","created":"2021-06-02","cited_by_count":46},{"id":"2206.07694","title":"DIRECTOR: Generator-Classifiers For Supervised Language Modeling","created":"2022-06-15","cited_by_count":38},{"id":"1609.00777","title":"Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access","created":"2016-09-03","cited_by_count":36},{"id":"2112.06346","title":"ValueNet: A New Dataset for Human Value Driven Dialogue System","created":"2021-12-12","cited_by_count":34},{"id":"1704.06497","title":"Bandit Structured Prediction for Neural Sequence-to-Sequence Learning","created":"2017-04-21","cited_by_count":31},{"id":"2005.07572","title":"Participatory Problem Formulation for Fairer Machine Learning Through Community Based System Dynamics","created":"2020-05-15","cited_by_count":31},{"id":"2303.18190","title":"Assessing Language Model Deployment with Risk Cards","created":"2023-03-31","cited_by_count":30},{"id":"2301.13771","title":"The Touch\\'e23-ValueEval Dataset for Identifying Human Values behind Arguments","created":"2023-01-31","cited_by_count":28},{"id":"1709.05467","title":"Acquiring Background Knowledge to Improve Moral Value Prediction","created":"2017-09-16","cited_by_count":22},{"id":"1912.05238","title":"BERT has a Moral Compass: Improvements of ethical and moral values of machines","created":"2019-12-11","cited_by_count":21},{"id":"1610.02891","title":"Personalizing a Dialogue System with Transfer Reinforcement Learning","created":"2016-10-10","cited_by_count":17},{"id":"2106.02692","title":"The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity","created":"2021-06-04","cited_by_count":16},{"id":"2112.13556","title":"Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modeling","created":"2021-12-27","cited_by_count":16},{"id":"1707.09118","title":"Counterfactual Learning from Bandit Feedback under Deterministic Logging: A Case Study in Statistical Machine Translation","created":"2017-07-28","cited_by_count":13},{"id":"2204.07603","title":"Learning to Adapt Domain Shifts of Moral Values via Instance Weighting","created":"2022-04-15","cited_by_count":11},{"id":"2208.03295","title":"Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls","created":"2022-08-05","cited_by_count":11},{"id":"1811.01866","title":"Do RNNs learn human-like abstract word order preferences?","created":"2018-11-05","cited_by_count":10},{"id":"1808.09658","title":"APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning","created":"2018-08-29","cited_by_count":9},{"id":"2109.11136","title":"Non-Parametric Online Learning from Human Feedback for Neural Machine Translation","created":"2021-09-23","cited_by_count":8},{"id":"2310.02457","title":"The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising \"Alignment\" in Large Language Models","created":"2023-10-03","cited_by_count":7},{"id":"1908.00286","title":"Reinforcement Learning for Personalized Dialogue Management","created":"2019-08-01","cited_by_count":6},{"id":"2110.02148","title":"NaRLE: Natural Language Models using Reinforcement Learning with Emotion Feedback","created":"2021-10-05","cited_by_count":5}],"next_cursor":null}