{"list":"other","total":53,"rows":[{"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489},{"id":"2305.13172","title":"Editing Large Language Models: Problems, Methods, and Opportunities","created":"2023-05-22","cited_by_count":372},{"id":"2310.12815","title":"Formalizing and Benchmarking Prompt Injection Attacks and Defenses","created":"2023-10-19","cited_by_count":364},{"id":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341},{"id":"2309.01431","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","created":"2023-09-04","cited_by_count":312},{"id":"2305.12740","title":"Can We Edit Factual Knowledge by In-Context Learning?","created":"2023-05-22","cited_by_count":285},{"id":"2307.09009","title":"How is ChatGPT's behavior changing over time?","created":"2023-07-18","cited_by_count":270},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246},{"id":"2307.12976","title":"Evaluating the Ripple Effects of Knowledge Editing in Language Models","created":"2023-07-24","cited_by_count":242},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194},{"id":"2402.05201","title":"The Effect of Sampling Temperature on Problem Solving in Large Language Models","created":"2024-02-07","cited_by_count":170},{"id":"2310.19156","title":"Poisoning Retrieval Corpora by Injecting Adversarial Passages","created":"2023-10-29","cited_by_count":159},{"id":"2311.01011","title":"Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game","created":"2023-11-02","cited_by_count":145},{"id":"2210.13701","title":"Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence","created":"2022-10-25","cited_by_count":144},{"id":"1902.08654","title":"What makes a good conversation? How controllable attributes affect human judgments","created":"2019-02-22","cited_by_count":140},{"id":"2401.05856","title":"Seven Failure Points When Engineering a Retrieval Augmented Generation System","created":"2024-01-11","cited_by_count":139},{"id":"2310.13345","title":"An LLM can Fool Itself: A Prompt-Based Adversarial Attack","created":"2023-10-20","cited_by_count":116},{"id":"2402.11436","title":"Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement","created":"2024-02-18","cited_by_count":114},{"id":"2307.09705","title":"CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility","created":"2023-07-19","cited_by_count":85},{"id":"2305.01651","title":"Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge","created":"2023-05-02","cited_by_count":67},{"id":"2402.11260","title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","created":"2024-02-17","cited_by_count":63},{"id":"2305.10266","title":"Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability","created":"2023-05-17","cited_by_count":62},{"id":"2012.03765","title":"Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks","created":"2020-12-07","cited_by_count":60},{"id":"2306.12420","title":"LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models","created":"2023-06-21","cited_by_count":60},{"id":"2202.02628","title":"Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation","created":"2022-02-05","cited_by_count":52},{"id":"2107.11136","title":"High Dimensional Differentially Private Stochastic Optimization with Heavy-tailed Data","created":"2021-07-23","cited_by_count":42},{"id":"2305.17826","title":"NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models","created":"2023-05-28","cited_by_count":37},{"id":"2211.13290","title":"SEAT: Stable and Explainable Attention","created":"2022-11-23","cited_by_count":25},{"id":"2311.02379","title":"Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Models","created":"2023-11-04","cited_by_count":22},{"id":"2301.09112","title":"Differentially Private Natural Language Models: Recent Advances and Future Directions","created":"2023-01-22","cited_by_count":20},{"id":"2205.13634","title":"BagFlip: A Certified Defense against Data Poisoning","created":"2022-05-26","cited_by_count":19},{"id":"2304.09762","title":"Practical Differentially Private and Byzantine-resilient Federated Learning","created":"2023-04-15","cited_by_count":18},{"id":"2004.03554","title":"Fine-Grained Named Entity Typing over Distantly Supervised Data Based on Refined Representations","created":"2020-04-07","cited_by_count":12},{"id":"2108.00331","title":"Faster Rates of Private Stochastic Convex Optimization","created":"2021-07-31","cited_by_count":12},{"id":"2208.03309","title":"Lethal Dose Conjecture on Data Poisoning","created":"2022-08-05","cited_by_count":12},{"id":"2310.08425","title":"Differentially Private Non-convex Learning for Multi-layer Neural Networks","created":"2023-10-12","cited_by_count":10},{"id":"1906.05612","title":"Antonym-Synonym Classification Based on New Sub-space Embeddings","created":"2019-06-13","cited_by_count":9},{"id":"1910.00482","title":"Estimating Smooth GLM in Non-interactive Local Differential Privacy Model with Public Unlabeled Data","created":"2019-10-01","cited_by_count":9},{"id":"2402.13087","title":"Revisiting Differentially Private Hyper-parameter Tuning","created":"2024-02-20","cited_by_count":5},{"id":"2305.09671","title":"Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks","created":"2023-05-07","cited_by_count":1},{"id":"2306.16415","title":"On Practical Aspects of Aggregation Defenses against Data Poisoning Attacks","created":"2023-06-28","cited_by_count":1}],"next_cursor":null}