{"list":"other","total":121,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"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":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2007.12626","title":"SummEval: Re-evaluating Summarization Evaluation","created":"2020-07-24","cited_by_count":674},{"id":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"2503.01743","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","created":"2025-03-03","cited_by_count":521},{"id":"2301.13848","title":"Benchmarking Large Language Models for News Summarization","created":"2023-01-31","cited_by_count":445},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"2111.09525","title":"SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization","created":"2021-11-18","cited_by_count":407},{"id":"2004.04228","title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries","created":"2020-04-08","cited_by_count":378},{"id":"2104.05938","title":"QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization","created":"2021-04-13","cited_by_count":365},{"id":"2403.12968","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","created":"2024-03-19","cited_by_count":348},{"id":"2209.12356","title":"News Summarization and Evaluation in the Era of GPT-3","created":"2022-09-26","cited_by_count":327},{"id":"2005.03754","title":"FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization","created":"2020-05-07","cited_by_count":293},{"id":"2107.00061","title":"All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text","created":"2021-06-30","cited_by_count":287},{"id":"2210.07197","title":"Towards a Unified Multi-Dimensional Evaluator for Text Generation","created":"2022-10-13","cited_by_count":264},{"id":"2103.12693","title":"QuestEval: Summarization Asks for Fact-based Evaluation","created":"2021-03-23","cited_by_count":244},{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205},{"id":"2105.06762","title":"DialogSum: A Real-Life Scenario Dialogue Summarization Dataset","created":"2021-05-14","cited_by_count":183},{"id":"2010.06595","title":"With Little Power Comes Great Responsibility","created":"2020-10-13","cited_by_count":142},{"id":"2212.07981","title":"Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation","created":"2022-12-15","cited_by_count":142},{"id":"1811.00347","title":"How2: A Large-scale Dataset for Multimodal Language Understanding","created":"2018-11-01","cited_by_count":138},{"id":"2103.06410","title":"MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization","created":"2021-03-11","cited_by_count":104},{"id":"2010.00490","title":"Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary","created":"2020-10-01","cited_by_count":88},{"id":"2305.17529","title":"MeetingBank: A Benchmark Dataset for Meeting Summarization","created":"2023-05-27","cited_by_count":84},{"id":"2407.00908","title":"FineSurE: Fine-grained Summarization Evaluation using LLMs","created":"2024-07-01","cited_by_count":83},{"id":"2002.09836","title":"Fill in the BLANC: Human-free quality estimation of document summaries","created":"2020-02-23","cited_by_count":82},{"id":"2302.03269","title":"PLACES: Prompting Language Models for Social Conversation Synthesis","created":"2023-02-07","cited_by_count":72},{"id":"2402.13249","title":"TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization","created":"2024-02-20","cited_by_count":66},{"id":"2110.10150","title":"Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents","created":"2021-10-16","cited_by_count":65},{"id":"1906.04165","title":"Leveraging BERT for Extractive Text Summarization on Lectures","created":"2019-06-07","cited_by_count":63},{"id":"2210.12467","title":"ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts","created":"2022-10-22","cited_by_count":59},{"id":"2311.06753","title":"AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs","created":"2023-11-12","cited_by_count":59},{"id":"2212.09739","title":"LENS: A Learnable Evaluation Metric for Text Simplification","created":"2022-12-19","cited_by_count":54},{"id":"2311.07052","title":"Towards the Law of Capacity Gap in Distilling Language Models","created":"2023-11-13","cited_by_count":44},{"id":"1906.07901","title":"Multimodal Abstractive Summarization for How2 Videos","created":"2019-06-19","cited_by_count":41},{"id":"1910.01335","title":"Topic-aware Pointer-Generator Networks for Summarizing Spoken Conversations","created":"2019-10-03","cited_by_count":41},{"id":"2108.13134","title":"Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation","created":"2021-08-30","cited_by_count":37},{"id":"2212.10525","title":"SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks","created":"2022-12-20","cited_by_count":35},{"id":"2106.08556","title":"Coreference-Aware Dialogue Summarization","created":"2021-06-16","cited_by_count":34},{"id":"2111.11894","title":"TWEETSUMM -- A Dialog Summarization Dataset for Customer Service","created":"2021-11-23","cited_by_count":34},{"id":"2310.19233","title":"Building Real-World Meeting Summarization Systems using Large Language Models: A Practical Perspective","created":"2023-10-30","cited_by_count":34},{"id":"2402.00841","title":"Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization?","created":"2024-02-01","cited_by_count":33},{"id":"2109.04609","title":"An Exploratory Study on Long Dialogue Summarization: What Works and What's Next","created":"2021-09-10","cited_by_count":28},{"id":"2108.13139","title":"CSDS: A Fine-Grained Chinese Dataset for Customer Service Dialogue Summarization","created":"2021-08-30","cited_by_count":27},{"id":"2109.05199","title":"A Survey on Multi-modal Summarization","created":"2021-09-11","cited_by_count":26},{"id":"2204.09890","title":"Spurious Correlations in Reference-Free Evaluation of Text Generation","created":"2022-04-21","cited_by_count":26},{"id":"2110.06263","title":"Speech Summarization using Restricted Self-Attention","created":"2021-10-12","cited_by_count":23},{"id":"2402.12025","title":"Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?","created":"2024-02-19","cited_by_count":23},{"id":"2306.13734","title":"The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios","created":"2023-06-23","cited_by_count":22},{"id":"1906.01361","title":"HighRES: Highlight-based Reference-less Evaluation of Summarization","created":"2019-06-04","cited_by_count":21},{"id":"2312.15475","title":"Evaluating Code Summarization Techniques: A New Metric and an Empirical Characterization","created":"2023-12-24","cited_by_count":21},{"id":"2106.02524","title":"CLIP: A Dataset for Extracting Action Items for Physicians from Hospital Discharge Notes","created":"2021-06-04","cited_by_count":20},{"id":"2406.16808","title":"Exploring the Capability of Mamba in Speech Applications","created":"2024-06-24","cited_by_count":20},{"id":"2303.02961","title":"Models See Hallucinations: Evaluating the Factuality in Video Captioning","created":"2023-03-06","cited_by_count":19},{"id":"2305.05280","title":"VCSUM: A Versatile Chinese Meeting Summarization Dataset","created":"2023-05-09","cited_by_count":18},{"id":"2309.08047","title":"Bias in News Summarization: Measures, Pitfalls and Corpora","created":"2023-09-14","cited_by_count":18},{"id":"2007.07860","title":"Dialect Diversity in Text Summarization on Twitter","created":"2020-07-15","cited_by_count":17},{"id":"2009.10298","title":"End-to-End Speech Recognition and Disfluency Removal","created":"2020-09-22","cited_by_count":16},{"id":"2402.17633","title":"From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions","created":"2024-02-27","cited_by_count":16},{"id":"2109.05160","title":"StreamHover: Livestream Transcript Summarization and Annotation","created":"2021-09-11","cited_by_count":15},{"id":"2405.06150","title":"Lost in Transcription: Identifying and Quantifying the Accuracy Biases of Automatic Speech Recognition Systems Against Disfluent Speech","created":"2024-05-10","cited_by_count":15},{"id":"2110.08583","title":"ASR4REAL: An extended benchmark for speech models","created":"2021-10-16","cited_by_count":14},{"id":"2011.04096","title":"Metrics also Disagree in the Low Scoring Range: Revisiting Summarization Evaluation Metrics","created":"2020-11-08","cited_by_count":13},{"id":"2103.15953","title":"TREC 2020 Podcasts Track Overview","created":"2021-03-29","cited_by_count":13},{"id":"2109.08232","title":"A Bag of Tricks for Dialogue Summarization","created":"2021-09-16","cited_by_count":13},{"id":"2010.08021","title":"MAST: Multimodal Abstractive Summarization with Trimodal Hierarchical Attention","created":"2020-10-15","cited_by_count":12},{"id":"2306.04216","title":"MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos","created":"2023-06-07","cited_by_count":12},{"id":"2307.15793","title":"Summaries, Highlights, and Action items: Design, implementation and evaluation of an LLM-powered meeting recap system","created":"2023-07-28","cited_by_count":12},{"id":"2303.00978","title":"Leveraging Large Text Corpora for End-to-End Speech Summarization","created":"2023-03-02","cited_by_count":11},{"id":"2502.08279","title":"What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations","created":"2025-02-12","cited_by_count":11},{"id":"2005.12143","title":"Adapting End-to-End Speech Recognition for Readable Subtitles","created":"2020-05-25","cited_by_count":10},{"id":"2501.00233","title":"Zero-Shot Strategies for Length-Controllable Summarization","created":"2024-12-31","cited_by_count":10},{"id":"2111.08201","title":"Attention-based Multi-hypothesis Fusion for Speech Summarization","created":"2021-11-16","cited_by_count":9},{"id":"2404.11124","title":"What's under the hood: Investigating Automatic Metrics on Meeting Summarization","created":"2024-04-17","cited_by_count":9},{"id":"2406.07494","title":"CADS: A Systematic Literature Review on the Challenges of Abstractive Dialogue Summarization","created":"2024-06-11","cited_by_count":9},{"id":"2410.14545","title":"Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization","created":"2024-10-18","cited_by_count":9},{"id":"2101.12406","title":"Fairness for Whom? Understanding the Reader's Perception of Fairness in Text Summarization","created":"2021-01-29","cited_by_count":8},{"id":"2203.11425","title":"Towards Abstractive Grounded Summarization of Podcast Transcripts","created":"2022-03-22","cited_by_count":8},{"id":"2408.14418","title":"MEDSAGE: Enhancing Robustness of Medical Dialogue Summarization to ASR Errors with LLM-generated Synthetic Dialogues","created":"2024-08-26","cited_by_count":8},{"id":"2410.16148","title":"PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters","created":"2024-10-21","cited_by_count":8},{"id":"2412.09818","title":"MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models","created":"2024-12-13","cited_by_count":8},{"id":"2209.13192","title":"Direct Speech Translation for Automatic Subtitling","created":"2022-09-27","cited_by_count":7},{"id":"2306.04233","title":"Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization","created":"2023-06-07","cited_by_count":7}],"next_cursor":"100"}