{"list":"other","total":98,"rows":[{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"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":"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":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"id":"2301.11305","title":"DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature","created":"2023-01-26","cited_by_count":726},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"2403.14403","title":"Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity","created":"2024-03-21","cited_by_count":451},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376},{"id":"2310.10501","title":"NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails","created":"2023-10-16","cited_by_count":365},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354},{"id":"2302.12813","title":"Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback","created":"2023-02-24","cited_by_count":353},{"id":"1901.09451","title":"Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting","created":"2019-01-27","cited_by_count":349},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2308.07107","title":"Large Language Models for Information Retrieval: A Survey","created":"2023-08-14","cited_by_count":331},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329},{"id":"2305.14739","title":"Trusting Your Evidence: Hallucinate Less with Context-aware Decoding","created":"2023-05-24","cited_by_count":327},{"id":"2310.03214","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","created":"2023-10-05","cited_by_count":318},{"id":"2304.09848","title":"Evaluating Verifiability in Generative Search Engines","created":"2023-04-19","cited_by_count":303},{"id":"2209.10063","title":"Generate rather than Retrieve: Large Language Models are Strong Context Generators","created":"2022-09-21","cited_by_count":298},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"1802.08908","title":"Scalable Private Learning with PATE","created":"2018-02-24","cited_by_count":269},{"id":"2311.09476","title":"ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems","created":"2023-11-16","cited_by_count":265},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2308.06394","title":"Detecting and Preventing Hallucinations in Large Vision Language Models","created":"2023-08-11","cited_by_count":256},{"id":"1711.08412","title":"Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes","created":"2017-11-22","cited_by_count":253},{"id":"2202.06991","title":"Transformer Memory as a Differentiable Search Index","created":"2022-02-14","cited_by_count":247},{"id":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202},{"id":"2402.00367","title":"Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration","created":"2024-02-01","cited_by_count":180},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177},{"id":"2305.14552","title":"Sources of Hallucination by Large Language Models on Inference Tasks","created":"2023-05-23","cited_by_count":169},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155},{"id":"2312.04724","title":"Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models","created":"2023-12-07","cited_by_count":138},{"id":"2310.04988","title":"The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediations","created":"2023-10-08","cited_by_count":131},{"id":"2312.03689","title":"Evaluating and Mitigating Discrimination in Language Model Decisions","created":"2023-12-06","cited_by_count":124},{"id":"2404.10198","title":"ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence","created":"2024-04-16","cited_by_count":113},{"id":"2310.05344","title":"SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF","created":"2023-10-09","cited_by_count":111},{"id":"2311.09677","title":"R-Tuning: Instructing Large Language Models to Say `I Don't Know'","created":"2023-11-16","cited_by_count":111},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107},{"id":"2308.14840","title":"Identifying and Mitigating the Security Risks of Generative AI","created":"2023-08-28","cited_by_count":91},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85},{"id":"2112.09238","title":"Benchmarking Differentially Private Synthetic Data Generation Algorithms","created":"2021-12-16","cited_by_count":81},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80},{"id":"2310.18491","title":"Publicly-Detectable Watermarking for Language Models","created":"2023-10-27","cited_by_count":76},{"id":"2102.13004","title":"Towards Unbiased and Accurate Deferral to Multiple Experts","created":"2021-02-25","cited_by_count":72},{"id":"2106.07153","title":"Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods","created":"2021-06-14","cited_by_count":59},{"id":"2312.14183","title":"On Early Detection of Hallucinations in Factual Question Answering","created":"2023-12-19","cited_by_count":56},{"id":"2103.06641","title":"Differentially Private Query Release Through Adaptive Projection","created":"2021-03-11","cited_by_count":52},{"id":"2402.15911","title":"PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails","created":"2024-02-24","cited_by_count":52},{"id":"1904.05233","title":"What's in a Name? Reducing Bias in Bios without Access to Protected Attributes","created":"2019-04-10","cited_by_count":51},{"id":"2402.14875","title":"What's in a Name? Auditing Large Language Models for Race and Gender Bias","created":"2024-02-21","cited_by_count":51},{"id":"2210.07543","title":"Watermarking Pre-trained Language Models with Backdooring","created":"2022-10-14","cited_by_count":50},{"id":"2310.11689","title":"Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs","created":"2023-10-18","cited_by_count":50},{"id":"2310.18168","title":"Personas as a Way to Model Truthfulness in Language Models","created":"2023-10-27","cited_by_count":47},{"id":"2202.08821","title":"Human-Algorithm Collaboration: Achieving Complementarity and Avoiding Unfairness","created":"2022-02-17","cited_by_count":45},{"id":"2212.11261","title":"Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias","created":"2022-12-21","cited_by_count":43},{"id":"2403.00742","title":"Dialect prejudice predicts AI decisions about people's character, employability, and criminality","created":"2024-03-01","cited_by_count":37},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32},{"id":"2310.06827","title":"Teaching Language Models to Hallucinate Less with Synthetic Tasks","created":"2023-10-10","cited_by_count":31},{"id":"2406.13138","title":"Large Language Models are Biased Because They Are Large Language Models","created":"2024-06-19","cited_by_count":26},{"id":"2305.14999","title":"The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models","created":"2023-05-24","cited_by_count":22},{"id":"2105.02274","title":"Rethinking Search: Making Domain Experts out of Dilettantes","created":"2021-05-05","cited_by_count":18},{"id":"2305.13514","title":"Small Language Models Improve Giants by Rewriting Their Outputs","created":"2023-05-22","cited_by_count":18},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11},{"id":"2204.04440","title":"Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks","created":"2022-04-09","cited_by_count":10},{"id":"2304.03545","title":"AI Model Disgorgement: Methods and Choices","created":"2023-04-07","cited_by_count":9},{"id":"2311.07424","title":"Hallucination Augmented Recitations for Language Models","created":"2023-11-13","cited_by_count":6},{"id":"2312.02337","title":"Measuring Distributional Shifts in Text: The Advantage of Language Model-Based Embeddings","created":"2023-12-04","cited_by_count":2}],"next_cursor":null}