{"list":"other","total":112,"rows":[{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"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":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2304.11406","title":"LaMP: When Large Language Models Meet Personalization","created":"2023-04-22","cited_by_count":437},{"id":"1803.06643","title":"The Web as a Knowledge-base for Answering Complex Questions","created":"2018-03-18","cited_by_count":410},{"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":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369},{"id":"2402.13178","title":"Benchmarking Retrieval-Augmented Generation for Medicine","created":"2024-02-20","cited_by_count":331},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302},{"id":"2003.07820","title":"Overview of the TREC 2019 deep learning track","created":"2020-03-17","cited_by_count":286},{"id":"2110.01052","title":"Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control","created":"2021-10-03","cited_by_count":271},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256},{"id":"2006.16923","title":"Large image datasets: A pyrrhic win for computer vision?","created":"2020-06-24","cited_by_count":237},{"id":"1804.11192","title":"Explainable Recommendation: A Survey and New Perspectives","created":"2018-04-30","cited_by_count":210},{"id":"1802.04422","title":"A comparative study of fairness-enhancing interventions in machine learning","created":"2018-02-13","cited_by_count":208},{"id":"2306.04634","title":"On the Reliability of Watermarks for Large Language Models","created":"2023-06-07","cited_by_count":189},{"id":"2403.18105","title":"Large Language Models for Education: A Survey and Outlook","created":"2024-03-26","cited_by_count":188},{"id":"2306.10193","title":"Conformal Language Modeling","created":"2023-06-16","cited_by_count":170},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163},{"id":"2310.19156","title":"Poisoning Retrieval Corpora by Injecting Adversarial Passages","created":"2023-10-29","cited_by_count":159},{"id":"2402.16893","title":"The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)","created":"2024-02-23","cited_by_count":159},{"id":"2305.18404","title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering","created":"2023-05-28","cited_by_count":139},{"id":"2402.10058","title":"Towards Safer Large Language Models through Machine Unlearning","created":"2024-02-15","cited_by_count":139},{"id":"2211.14876","title":"Dense Text Retrieval based on Pretrained Language Models: A Survey","created":"2022-11-27","cited_by_count":136},{"id":"2009.03015","title":"Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding","created":"2020-09-07","cited_by_count":130},{"id":"2312.03718","title":"Large Language Models in Law: A Survey","created":"2023-11-26","cited_by_count":128},{"id":"2401.12794","title":"Benchmarking LLMs via Uncertainty Quantification","created":"2024-01-23","cited_by_count":126},{"id":"2404.07103","title":"Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs","created":"2024-04-10","cited_by_count":119},{"id":"2408.10343","title":"LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain","created":"2024-08-19","cited_by_count":118},{"id":"2311.07361","title":"The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4","created":"2023-11-13","cited_by_count":112},{"id":"2312.07913","title":"A Survey of Text Watermarking in the Era of Large Language Models","created":"2023-12-13","cited_by_count":112},{"id":"2304.03879","title":"GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation","created":"2023-04-08","cited_by_count":103},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102},{"id":"2405.10051","title":"MarkLLM: An Open-Source Toolkit for LLM Watermarking","created":"2024-05-16","cited_by_count":95},{"id":"2405.20978","title":"Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training","created":"2024-05-31","cited_by_count":89},{"id":"2409.10102","title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","created":"2024-09-16","cited_by_count":83},{"id":"2305.01904","title":"Robust Multi-bit Natural Language Watermarking through Invariant Features","created":"2023-05-03","cited_by_count":82},{"id":"2302.13425","title":"A Survey on Uncertainty Quantification Methods for Deep Learning","created":"2023-02-26","cited_by_count":81},{"id":"2312.04469","title":"On the Learnability of Watermarks for Language Models","created":"2023-12-07","cited_by_count":81},{"id":"2310.12362","title":"REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models","created":"2023-10-18","cited_by_count":78},{"id":"2310.18491","title":"Publicly-Detectable Watermarking for Language Models","created":"2023-10-27","cited_by_count":76},{"id":"2402.17840","title":"Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems","created":"2024-02-27","cited_by_count":76},{"id":"2403.13485","title":"An Entropy-based Text Watermarking Detection Method","created":"2024-03-20","cited_by_count":75},{"id":"2405.01769","title":"A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law","created":"2024-05-02","cited_by_count":74},{"id":"2404.04302","title":"CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering","created":"2024-04-04","cited_by_count":72},{"id":"2312.00273","title":"Mark My Words: Analyzing and Evaluating Language Model Watermarks","created":"2023-12-01","cited_by_count":71},{"id":"2403.01216","title":"API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access","created":"2024-03-02","cited_by_count":69},{"id":"2404.13081","title":"SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs","created":"2024-04-17","cited_by_count":67},{"id":"2402.08416","title":"Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning","created":"2024-02-13","cited_by_count":64},{"id":"2308.00221","title":"Advancing Beyond Identification: Multi-bit Watermark for Large Language Models","created":"2023-08-01","cited_by_count":57},{"id":"2310.09241","title":"Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration","created":"2023-10-13","cited_by_count":52},{"id":"2406.14773","title":"Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data","created":"2024-06-20","cited_by_count":52},{"id":"2204.04859","title":"A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges","created":"2022-04-11","cited_by_count":50},{"id":"1904.07531","title":"Understanding the Behaviors of BERT in Ranking","created":"2019-04-16","cited_by_count":49},{"id":"2110.12925","title":"CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning","created":"2021-10-25","cited_by_count":47},{"id":"2112.07873","title":"Tracing Text Provenance via Context-Aware Lexical Substitution","created":"2021-12-15","cited_by_count":45},{"id":"2402.08577","title":"Test-Time Backdoor Attacks on Multimodal Large Language Models","created":"2024-02-13","cited_by_count":40},{"id":"2310.18347","title":"PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter","created":"2023-10-23","cited_by_count":38},{"id":"2411.14110","title":"Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications","created":"2024-11-21","cited_by_count":37},{"id":"1902.06787","title":"Regularizing Black-box Models for Improved Interpretability","created":"2019-02-18","cited_by_count":35},{"id":"2104.13640","title":"Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankers","created":"2021-04-28","cited_by_count":35},{"id":"2010.02557","title":"PolicyQA: A Reading Comprehension Dataset for Privacy Policies","created":"2020-10-06","cited_by_count":34},{"id":"2308.14401","title":"CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models","created":"2023-08-28","cited_by_count":34},{"id":"2403.19964","title":"FairRAG: Fair Human Generation via Fair Retrieval Augmentation","created":"2024-03-29","cited_by_count":34},{"id":"2311.07138","title":"WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models","created":"2023-11-13","cited_by_count":32},{"id":"2306.06815","title":"TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models","created":"2023-06-12","cited_by_count":31},{"id":"2010.05821","title":"Open-sourced Dataset Protection via Backdoor Watermarking","created":"2020-10-12","cited_by_count":30},{"id":"2409.08045","title":"Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking","created":"2024-09-12","cited_by_count":30},{"id":"2005.00372","title":"Do Neural Ranking Models Intensify Gender Bias?","created":"2020-05-01","cited_by_count":29},{"id":"2101.04109","title":"Explain and Predict, and then Predict Again","created":"2021-01-11","cited_by_count":29},{"id":"2310.08920","title":"Embarrassingly Simple Text Watermarks","created":"2023-10-13","cited_by_count":29},{"id":"2409.19804","title":"Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems","created":"2024-09-29","cited_by_count":26},{"id":"2307.04642","title":"TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal Prediction","created":"2023-07-07","cited_by_count":25},{"id":"2404.15639","title":"CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code","created":"2024-04-24","cited_by_count":24},{"id":"2011.00696","title":"ABNIRML: Analyzing the Behavior of Neural IR Models","created":"2020-11-02","cited_by_count":23},{"id":"2411.01705","title":"Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors","created":"2024-11-03","cited_by_count":23},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22},{"id":"2406.11497","title":"CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG","created":"2024-06-17","cited_by_count":22},{"id":"2305.19329","title":"Mitigating Test-Time Bias for Fair Image Retrieval","created":"2023-05-23","cited_by_count":20},{"id":"2405.00449","title":"RAG-based Explainable Prediction of Road Users Behaviors for Automated Driving using Knowledge Graphs and Large Language Models","created":"2024-05-01","cited_by_count":20},{"id":"2404.03192","title":"Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers","created":"2024-04-04","cited_by_count":17},{"id":"2410.03537","title":"Ward: Provable RAG Dataset Inference via LLM Watermarks","created":"2024-10-04","cited_by_count":16},{"id":"2410.17519","title":"Large Language Models Still Exhibit Bias in Long Text","created":"2024-10-23","cited_by_count":16},{"id":"2407.04411","title":"Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs","created":"2024-07-05","cited_by_count":15},{"id":"2409.11598","title":"Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation","created":"2024-09-17","cited_by_count":15}],"next_cursor":"100"}