{"list":"other","total":82,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"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":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"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":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"1312.6211","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","created":"2013-12-21","cited_by_count":722},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"2004.09813","title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation","created":"2020-04-21","cited_by_count":593},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505},{"id":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"2012.00955","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","created":"2020-12-02","cited_by_count":445},{"id":"1706.04115","title":"Zero-Shot Relation Extraction via Reading Comprehension","created":"2017-06-13","cited_by_count":426},{"id":"2306.04751","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","created":"2023-06-07","cited_by_count":408},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401},{"id":"2004.10645","title":"AmbigQA: Answering Ambiguous Open-domain Questions","created":"2020-04-22","cited_by_count":390},{"id":"2309.07875","title":"Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions","created":"2023-09-14","cited_by_count":387},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364},{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285},{"id":"2006.09462","title":"Selective Question Answering under Domain Shift","created":"2020-06-16","cited_by_count":238},{"id":"2406.18510","title":"WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models","created":"2024-06-26","cited_by_count":223},{"id":"2012.14983","title":"Reducing conversational agents' overconfidence through linguistic calibration","created":"2020-12-30","cited_by_count":210},{"id":"2205.12628","title":"Are Large Pre-Trained Language Models Leaking Your Personal Information?","created":"2022-05-25","cited_by_count":200},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199},{"id":"2308.13387","title":"Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs","created":"2023-08-25","cited_by_count":184},{"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":"2010.07487","title":"Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI","created":"2020-10-15","cited_by_count":167},{"id":"2109.06157","title":"SituatedQA: Incorporating Extra-Linguistic Contexts into QA","created":"2021-09-13","cited_by_count":145},{"id":"2010.02428","title":"UnQovering Stereotyping Biases via Underspecified Questions","created":"2020-10-06","cited_by_count":126},{"id":"1710.10723","title":"Simple and Effective Multi-Paragraph Reading Comprehension","created":"2017-10-29","cited_by_count":120},{"id":"1805.04655","title":"Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information","created":"2018-05-12","cited_by_count":115},{"id":"2310.13771","title":"Copyright Violations and Large Language Models","created":"2023-10-20","cited_by_count":108},{"id":"2311.09469","title":"Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs","created":"2023-11-16","cited_by_count":98},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89},{"id":"2109.01653","title":"CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge","created":"2021-09-03","cited_by_count":88},{"id":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77},{"id":"2211.17257","title":"CREPE: Open-Domain Question Answering with False Presuppositions","created":"2022-11-30","cited_by_count":72},{"id":"2212.07769","title":"CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models","created":"2022-12-15","cited_by_count":69},{"id":"1911.00841","title":"Question Answering for Privacy Policies: Combining Computational and Legal Perspectives","created":"2019-11-03","cited_by_count":67},{"id":"2203.00211","title":"Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings","created":"2022-03-01","cited_by_count":66},{"id":"2305.13712","title":"Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models","created":"2023-05-23","cited_by_count":61},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61},{"id":"2405.18540","title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning","created":"2024-05-28","cited_by_count":54},{"id":"2212.10003","title":"(QA)$^2$: Question Answering with Questionable Assumptions","created":"2022-12-20","cited_by_count":51},{"id":"2403.12958","title":"Dated Data: Tracing Knowledge Cutoffs in Large Language Models","created":"2024-03-19","cited_by_count":51},{"id":"2402.03563","title":"Distinguishing the Knowable from the Unknowable with Language Models","created":"2024-02-05","cited_by_count":47},{"id":"2010.11915","title":"Challenges in Information-Seeking QA: Unanswerable Questions and Paragraph Retrieval","created":"2020-10-22","cited_by_count":44},{"id":"2104.06828","title":"Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge","created":"2021-04-14","cited_by_count":40},{"id":"2212.10409","title":"ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations","created":"2022-12-20","cited_by_count":36},{"id":"2305.08005","title":"Beyond the Safeguards: Exploring the Security Risks of ChatGPT","created":"2023-05-13","cited_by_count":36},{"id":"2402.11889","title":"ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding","created":"2024-02-19","cited_by_count":32},{"id":"2303.18190","title":"Assessing Language Model Deployment with Risk Cards","created":"2023-03-31","cited_by_count":30},{"id":"2305.09800","title":"Mirages: On Anthropomorphism in Dialogue Systems","created":"2023-05-16","cited_by_count":30},{"id":"2406.15948","title":"Teaching LLMs to Abstain across Languages via Multilingual Feedback","created":"2024-06-22","cited_by_count":14},{"id":"2403.12862","title":"Epistemology of Language Models: Do Language Models Have Holistic Knowledge?","created":"2024-03-19","cited_by_count":9}],"next_cursor":null}