{"list":"other","total":104,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"1808.09781","title":"Self-Attentive Sequential Recommendation","created":"2018-08-20","cited_by_count":1184},{"id":"1708.05031","title":"Neural Collaborative Filtering","created":"2017-08-16","cited_by_count":1111},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"2309.15217","title":"Ragas: Automated Evaluation of Retrieval Augmented Generation","created":"2023-09-26","cited_by_count":418},{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417},{"id":"2305.19860","title":"A Survey on Large Language Models for Recommendation","created":"2023-05-31","cited_by_count":379},{"id":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361},{"id":"2305.08845","title":"Large Language Models are Zero-Shot Rankers for Recommender Systems","created":"2023-05-15","cited_by_count":309},{"id":"2305.16739","title":"AlignScore: Evaluating Factual Consistency with a Unified Alignment Function","created":"2023-05-26","cited_by_count":288},{"id":"2103.12693","title":"QuestEval: Summarization Asks for Fact-based Evaluation","created":"2021-03-23","cited_by_count":244},{"id":"2406.18403","title":"LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks","created":"2024-06-26","cited_by_count":243},{"id":"2010.03240","title":"Bias and Debias in Recommender System: A Survey and Future Directions","created":"2020-10-07","cited_by_count":240},{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186},{"id":"2006.06264","title":"Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics","created":"2020-06-11","cited_by_count":158},{"id":"2004.00646","title":"A Survey on Conversational Recommender Systems","created":"2020-04-01","cited_by_count":143},{"id":"2308.10053","title":"Large Language Models as Zero-Shot Conversational Recommenders","created":"2023-08-19","cited_by_count":127},{"id":"2310.03668","title":"GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction","created":"2023-10-05","cited_by_count":119},{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118},{"id":"2407.10457","title":"The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism","created":"2024-07-15","cited_by_count":116},{"id":"2004.14564","title":"Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing","created":"2020-04-30","cited_by_count":115},{"id":"2402.13950","title":"Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning","created":"2024-02-21","cited_by_count":110},{"id":"2309.17249","title":"Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering","created":"2023-09-29","cited_by_count":94},{"id":"2403.02839","title":"An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4","created":"2024-03-05","cited_by_count":94},{"id":"2304.00723","title":"Exploring the Use of Large Language Models for Reference-Free Text Quality Evaluation: An Empirical Study","created":"2023-04-03","cited_by_count":85},{"id":"2307.16372","title":"LP-MusicCaps: LLM-Based Pseudo Music Captioning","created":"2023-07-31","cited_by_count":83},{"id":"1901.07555","title":"Managing Popularity Bias in Recommender Systems with Personalized Re-ranking","created":"2019-01-22","cited_by_count":82},{"id":"2310.19596","title":"LLMaAA: Making Large Language Models as Active Annotators","created":"2023-10-30","cited_by_count":79},{"id":"2306.08189","title":"Language models are not naysayers: An analysis of language models on negation benchmarks","created":"2023-06-14","cited_by_count":74},{"id":"2402.16153","title":"ChatMusician: Understanding and Generating Music Intrinsically with LLM","created":"2024-02-25","cited_by_count":68},{"id":"1802.08452","title":"Sequence-Aware Recommender Systems","created":"2018-02-23","cited_by_count":58},{"id":"2210.12563","title":"On the Limitations of Reference-Free Evaluations of Generated Text","created":"2022-10-22","cited_by_count":52},{"id":"2109.05771","title":"Perturbation CheckLists for Evaluating NLG Evaluation Metrics","created":"2021-09-13","cited_by_count":50},{"id":"2210.07626","title":"BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation","created":"2022-10-14","cited_by_count":48},{"id":"2309.08730","title":"MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response","created":"2023-09-15","cited_by_count":45},{"id":"2408.01337","title":"MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models","created":"2024-08-02","cited_by_count":44},{"id":"1710.03208","title":"Current Challenges and Visions in Music Recommender Systems Research","created":"2017-10-09","cited_by_count":42},{"id":"2108.12463","title":"Automatic Text Evaluation through the Lens of Wasserstein Barycenters","created":"2021-08-27","cited_by_count":38},{"id":"1803.09587","title":"Evaluation of Session-based Recommendation Algorithms","created":"2018-03-26","cited_by_count":37},{"id":"2201.11176","title":"DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence","created":"2022-01-26","cited_by_count":36},{"id":"2202.08479","title":"On the Evaluation Metrics for Paraphrase Generation","created":"2022-02-17","cited_by_count":32},{"id":"2205.11127","title":"Fairness in Recommender Systems: Research Landscape and Future Directions","created":"2022-05-23","cited_by_count":30},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29},{"id":"2401.10545","title":"Understanding Biases in ChatGPT-based Recommender Systems: Provider Fairness, Temporal Stability, and Recency","created":"2024-01-19","cited_by_count":28},{"id":"2408.00802","title":"Leveraging LLM Reasoning Enhances Personalized Recommender Systems","created":"2024-07-22","cited_by_count":28},{"id":"2411.12405","title":"Evaluating the Prompt Steerability of Large Language Models","created":"2024-11-19","cited_by_count":27},{"id":"2312.04021","title":"A Study on the Calibration of In-context Learning","created":"2023-12-07","cited_by_count":22},{"id":"2404.12008","title":"How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective","created":"2024-04-18","cited_by_count":21},{"id":"2502.10362","title":"CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages","created":"2025-02-14","cited_by_count":21},{"id":"2208.07316","title":"MENLI: Robust Evaluation Metrics from Natural Language Inference","created":"2022-08-15","cited_by_count":18},{"id":"2402.15623","title":"Language-Based User Profiles for Recommendation","created":"2024-02-23","cited_by_count":18},{"id":"2304.04250","title":"Editable User Profiles for Controllable Text Recommendation","created":"2023-04-09","cited_by_count":16},{"id":"2201.10528","title":"Explainability in Music Recommender Systems","created":"2022-01-25","cited_by_count":15},{"id":"2405.06524","title":"Prompting Large Language Models with Knowledge Graphs for Question Answering Involving Long-tail Facts","created":"2024-05-10","cited_by_count":14},{"id":"2403.07260","title":"LaERC-S: Improving LLM-based Emotion Recognition in Conversation with Speaker Characteristics","created":"2024-03-12","cited_by_count":13},{"id":"2409.15173","title":"Recommendation with Generative Models","created":"2024-09-18","cited_by_count":13},{"id":"2107.11803","title":"Content-driven Music Recommendation: Evolution, State of the Art, and Challenges","created":"2021-07-25","cited_by_count":12},{"id":"2312.16015","title":"A Comprehensive Survey of Evaluation Techniques for Recommendation Systems","created":"2023-12-26","cited_by_count":12},{"id":"2310.15511","title":"KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval","created":"2023-10-24","cited_by_count":11},{"id":"2504.06667","title":"Toward Holistic Evaluation of Recommender Systems Powered by Generative Models","created":"2025-04-09","cited_by_count":11},{"id":"2410.18870","title":"End-to-end Training for Recommendation with Language-based User Profiles","created":"2024-10-24","cited_by_count":10},{"id":"2410.16780","title":"Beyond Retrieval: Generating Narratives in Conversational Recommender Systems","created":"2024-10-22","cited_by_count":8},{"id":"2409.19723","title":"Revealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on Dialogues","created":"2024-09-29","cited_by_count":7},{"id":"2410.03264","title":"Enriching Music Descriptions with a Finetuned-LLM and Metadata for Text-to-Music Retrieval","created":"2024-10-04","cited_by_count":7},{"id":"2410.17233","title":"ICPL: Few-shot In-context Preference Learning via LLMs","created":"2024-10-22","cited_by_count":7},{"id":"2508.15030","title":"Collab-REC: An LLM-based Agentic Framework for Balancing Recommendations in Tourism","created":"2025-08-20","cited_by_count":7},{"id":"2010.06325","title":"Modeling the Music Genre Perception across Language-Bound Cultures","created":"2020-10-13","cited_by_count":6},{"id":"2303.06944","title":"A Human Subject Study of Named Entity Recognition (NER) in Conversational Music Recommendation Queries","created":"2023-03-13","cited_by_count":6},{"id":"2404.18640","title":"Going Beyond Popularity and Positivity Bias: Correcting for Multifactorial Bias in Recommender Systems","created":"2024-04-29","cited_by_count":6},{"id":"2502.15229","title":"User Experience with LLM-powered Conversational Recommendation Systems: A Case of Music Recommendation","created":"2025-02-21","cited_by_count":6},{"id":"2505.00886","title":"Towards Explainable Temporal User Profiling with LLMs","created":"2025-05-01","cited_by_count":6},{"id":"2009.07755","title":"Multilingual Music Genre Embeddings for Effective Cross-Lingual Music Item Annotation","created":"2020-09-16","cited_by_count":5},{"id":"2110.07354","title":"Music Playlist Title Generation: A Machine-Translation Approach","created":"2021-10-03","cited_by_count":5},{"id":"2209.06126","title":"A Stakeholder-Centered View on Fairness in Music Recommender Systems","created":"2022-09-08","cited_by_count":5},{"id":"2307.10702","title":"A Constraint-based Recommender System via RDF Knowledge Graphs","created":"2023-07-20","cited_by_count":5},{"id":"2404.11793","title":"Enhancing Argument Summarization: Prioritizing Exhaustiveness in Key Point Generation and Introducing an Automatic Coverage Evaluation Metric","created":"2024-04-17","cited_by_count":5},{"id":"2410.23136","title":"Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning","created":"2024-10-30","cited_by_count":5},{"id":"2507.15826","title":"Just Ask for Music (JAM): Multimodal and Personalized Natural Language Music Recommendation","created":"2025-07-21","cited_by_count":5},{"id":"1912.06933","title":"Global and country-specific mainstreaminess measures: Definitions, analysis, and usage for improving personalized music recommendation systems","created":"2019-12-14","cited_by_count":4},{"id":"2412.11851","title":"A Benchmark and Robustness Study of In-Context-Learning with Large Language Models in Music Entity Detection","created":"2024-12-16","cited_by_count":4},{"id":"1907.08698","title":"Leveraging Knowledge Bases And Parallel Annotations For Music Genre Translation","created":"2019-07-18","cited_by_count":3},{"id":"2311.10635","title":"Ex2Vec: Characterizing Users and Items from the Mere Exposure Effect","created":"2023-11-17","cited_by_count":3},{"id":"2405.01417","title":"Modeling Activity-Driven Music Listening with PACE","created":"2024-05-02","cited_by_count":3},{"id":"2501.05894","title":"Text2Playlist: Generating Personalized Playlists from Text on Deezer","created":"2025-01-10","cited_by_count":3},{"id":"2509.09685","title":"TalkPlayData 2: An Agentic Synthetic Data Pipeline for Multimodal Conversational Music Recommendation","created":"2025-08-18","cited_by_count":3},{"id":"2408.16430","title":"Do Recommender Systems Promote Local Music? A Reproducibility Study Using Music Streaming Data","created":"2024-08-29","cited_by_count":2},{"id":"2410.03375","title":"SoundSignature: What Type of Music Do You Like?","created":"2024-10-04","cited_by_count":2}],"next_cursor":"100"}