{"list":"other","total":81,"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2404.16130","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","created":"2024-04-24","cited_by_count":1453},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2212.10509","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","created":"2022-12-20","cited_by_count":923},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595},{"id":"1907.09190","title":"ELI5: Long Form Question Answering","created":"2019-07-22","cited_by_count":575},{"id":"2401.18059","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","created":"2024-01-31","cited_by_count":532},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"1806.10758","title":"A Benchmark for Interpretability Methods in Deep Neural Networks","created":"2018-06-28","cited_by_count":476},{"id":"2310.06839","title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","created":"2023-10-10","cited_by_count":453},{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369},{"id":"2305.14739","title":"Trusting Your Evidence: Hallucinate Less with Context-aware Decoding","created":"2023-05-24","cited_by_count":327},{"id":"2408.08921","title":"Graph Retrieval-Augmented Generation: A Survey","created":"2024-08-15","cited_by_count":324},{"id":"2212.14024","title":"Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP","created":"2022-12-28","cited_by_count":318},{"id":"2210.02410","title":"The Vendi Score: A Diversity Evaluation Metric for Machine Learning","created":"2022-10-05","cited_by_count":311},{"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":"2404.02060","title":"Long-context LLMs Struggle with Long In-context Learning","created":"2024-04-02","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":"2311.09476","title":"ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems","created":"2023-11-16","cited_by_count":265},{"id":"2403.10131","title":"RAFT: Adapting Language Model to Domain Specific RAG","created":"2024-03-15","cited_by_count":262},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2204.06092","title":"ASQA: Factoid Questions Meet Long-Form Answers","created":"2022-04-12","cited_by_count":234},{"id":"2307.11088","title":"L-Eval: Instituting Standardized Evaluation for Long Context Language Models","created":"2023-07-20","cited_by_count":233},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"2011.14878","title":"Explaining by Removing: A Unified Framework for Model Explanation","created":"2020-11-21","cited_by_count":218},{"id":"2402.14848","title":"Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models","created":"2024-02-19","cited_by_count":152},{"id":"2306.02552","title":"User Behavior Simulation with Large Language Model based Agents","created":"2023-06-05","cited_by_count":140},{"id":"2410.05983","title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG","created":"2024-10-08","cited_by_count":123},{"id":"2212.08037","title":"Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models","created":"2022-12-15","cited_by_count":112},{"id":"1409.7938","title":"Lazier Than Lazy Greedy","created":"2014-09-28","cited_by_count":99},{"id":"2409.00729","title":"ContextCite: Attributing Model Generation to Context","created":"2024-09-01","cited_by_count":98},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97},{"id":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89},{"id":"2407.08223","title":"Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting","created":"2024-07-11","cited_by_count":77},{"id":"2410.04343","title":"Inference Scaling for Long-Context Retrieval Augmented Generation","created":"2024-10-06","cited_by_count":65},{"id":"2108.11044","title":"Pseudo Relevance Feedback with Deep Language Models and Dense Retrievers: Successes and Pitfalls","created":"2021-08-25","cited_by_count":26},{"id":"2503.00353","title":"U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack","created":"2025-03-01","cited_by_count":20},{"id":"2104.08912","title":"The Simpson's Paradox in the Offline Evaluation of Recommendation Systems","created":"2021-04-18","cited_by_count":16},{"id":"2403.12499","title":"Listwise Generative Retrieval Models via a Sequential Learning Process","created":"2024-03-19","cited_by_count":11},{"id":"2106.12460","title":"Extractive Explanations for Interpretable Text Ranking","created":"2021-06-23","cited_by_count":9},{"id":"2502.09017","title":"Diversity Enhances an LLM's Performance in RAG and Long-context Task","created":"2025-02-13","cited_by_count":8},{"id":"2511.05385","title":"TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework","created":"2025-11-07","cited_by_count":7},{"id":"2104.13453","title":"Meta-evaluation of Conversational Search Evaluation Metrics","created":"2021-04-27","cited_by_count":6},{"id":"2410.16229","title":"Building A Coding Assistant via the Retrieval-Augmented Language Model","created":"2024-10-21","cited_by_count":5},{"id":"2507.21934","title":"Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation","created":"2025-07-29","cited_by_count":2},{"id":"2403.09180","title":"Online and Offline Evaluation in Search Clarification","created":"2024-03-14","cited_by_count":1}],"next_cursor":null}