{"list":"other","total":64,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"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":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"2303.15056","title":"ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks","created":"2023-03-27","cited_by_count":870},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"2003.06713","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","created":"2020-03-14","cited_by_count":376},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333},{"id":"2305.13534","title":"How Language Model Hallucinations Can Snowball","created":"2023-05-22","cited_by_count":311},{"id":"2401.00595","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","created":"2023-12-31","cited_by_count":310},{"id":"2003.07820","title":"Overview of the TREC 2019 deep learning track","created":"2020-03-17","cited_by_count":286},{"id":"2401.14887","title":"The Power of Noise: Redefining Retrieval for RAG Systems","created":"2024-01-26","cited_by_count":281},{"id":"2402.07867","title":"PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models","created":"2024-02-12","cited_by_count":267},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266},{"id":"2308.07308","title":"LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked","created":"2023-08-14","cited_by_count":244},{"id":"2410.05451","title":"SecAlign: Defending Against Prompt Injection with Preference Optimization","created":"2024-10-07","cited_by_count":210},{"id":"2102.07662","title":"Overview of the TREC 2020 deep learning track","created":"2021-02-15","cited_by_count":196},{"id":"2501.18837","title":"Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming","created":"2025-01-31","cited_by_count":181},{"id":"2207.05987","title":"DocPrompting: Generating Code by Retrieving the Docs","created":"2022-07-13","cited_by_count":153},{"id":"2403.04783","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","created":"2024-03-02","cited_by_count":145},{"id":"2403.17710","title":"Optimization-based Prompt Injection Attack to LLM-as-a-Judge","created":"2024-03-26","cited_by_count":143},{"id":"2210.02627","title":"Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering","created":"2022-10-06","cited_by_count":127},{"id":"2507.15219","title":"PromptArmor: Simple yet Effective Prompt Injection Defenses","created":"2025-07-21","cited_by_count":108},{"id":"2312.17673","title":"Jatmo: Prompt Injection Defense by Task-Specific Finetuning","created":"2023-12-29","cited_by_count":106},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88},{"id":"2403.13031","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","created":"2024-03-19","cited_by_count":68},{"id":"2404.13948","title":"Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations","created":"2024-04-22","cited_by_count":65},{"id":"2310.07554","title":"A Multi-Task Embedder For Retrieval Augmented LLMs","created":"2023-10-11","cited_by_count":64},{"id":"2205.02832","title":"Entity Cloze By Date: What LMs Know About Unseen Entities","created":"2022-05-05","cited_by_count":55},{"id":"2308.01990","title":"From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application?","created":"2023-08-03","cited_by_count":55},{"id":"2502.07557","title":"JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation","created":"2025-02-11","cited_by_count":54},{"id":"2501.15145","title":"PromptShield: Deployable Detection for Prompt Injection Attacks","created":"2025-01-25","cited_by_count":50},{"id":"2405.20485","title":"Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation","created":"2024-05-30","cited_by_count":49},{"id":"2204.01321","title":"PRADA: Practical Black-Box Adversarial Attacks against Neural Ranking Models","created":"2022-04-04","cited_by_count":44},{"id":"2309.00841","title":"LeanContext: Cost-Efficient Domain-Specific Question Answering Using LLMs","created":"2023-09-02","cited_by_count":40},{"id":"2209.06506","title":"Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Models","created":"2022-09-14","cited_by_count":37},{"id":"2406.16828","title":"Ragnar\\\"ok: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track","created":"2024-06-24","cited_by_count":32},{"id":"2501.11759","title":"Poison-RAG: Adversarial Data Poisoning Attacks on Retrieval-Augmented Generation in Recommender Systems","created":"2025-01-20","cited_by_count":32},{"id":"2308.09861","title":"Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method","created":"2023-08-19","cited_by_count":29},{"id":"2410.22284","title":"Embedding-based classifiers can detect prompt injection attacks","created":"2024-10-29","cited_by_count":27},{"id":"2410.22832","title":"HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models","created":"2024-10-30","cited_by_count":27},{"id":"2402.15833","title":"Prompt Perturbation Consistency Learning for Robust Language Models","created":"2024-02-24","cited_by_count":26},{"id":"2501.07391","title":"Enhancing Retrieval-Augmented Generation: A Study of Best Practices","created":"2025-01-13","cited_by_count":23},{"id":"2507.10865","title":"Overview of the TREC 2022 deep learning track","created":"2025-07-10","cited_by_count":22},{"id":"2410.18141","title":"SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback","created":"2024-10-22","cited_by_count":19},{"id":"2305.01860","title":"Towards Imperceptible Document Manipulations against Neural Ranking Models","created":"2023-05-03","cited_by_count":18},{"id":"2206.11724","title":"BERT Rankers are Brittle: a Study using Adversarial Document Perturbations","created":"2022-06-23","cited_by_count":16},{"id":"2507.06956","title":"Investigating the Robustness of Retrieval-Augmented Generation at the Query Level","created":"2025-07-09","cited_by_count":11},{"id":"2305.14493","title":"Do prompt positions really matter?","created":"2023-05-23","cited_by_count":5},{"id":"2410.21337","title":"Fine-tuned Large Language Models (LLMs): Improved Prompt Injection Attacks Detection","created":"2024-10-28","cited_by_count":5},{"id":"2412.16382","title":"EMPRA: Embedding Perturbation Rank Attack against Neural Ranking Models","created":"2024-12-20","cited_by_count":5},{"id":"2506.10802","title":"Constructing and Evaluating Declarative RAG Pipelines in PyTerrier","created":"2025-06-12","cited_by_count":5},{"id":"2507.15042","title":"DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection","created":"2025-07-20","cited_by_count":5},{"id":"2508.15283","title":"Adversarial Attacks against Neural Ranking Models via In-Context Learning","created":"2025-08-21","cited_by_count":4}],"next_cursor":null}