{"total":74,"rows":[{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2406.13340","title":"SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words","created":"2024-06-19","cited_by_count":68,"area":null},{"id":"2502.08826","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","created":"2025-02-12","cited_by_count":42,"area":"rag"},{"id":"2109.03381","title":"Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering","created":"2021-09-08","cited_by_count":39,"area":null},{"id":"2109.12072","title":"SD-QA: Spoken Dialectal Question Answering for the Real World","created":"2021-09-24","cited_by_count":38,"area":null},{"id":"2204.14272","title":"End-to-end Spoken Conversational Question Answering: Task, Dataset and Model","created":"2022-04-29","cited_by_count":37,"area":null},{"id":"2212.10525","title":"SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks","created":"2022-12-20","cited_by_count":35,"area":null},{"id":"2106.02182","title":"Self-supervised Dialogue Learning for Spoken Conversational Question Answering","created":"2021-06-04","cited_by_count":28,"area":null},{"id":"2109.04275","title":"M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining","created":"2021-09-09","cited_by_count":26,"area":null},{"id":"2102.08345","title":"NoiseQA: Challenge Set Evaluation for User-Centric Question Answering","created":"2021-02-16","cited_by_count":25,"area":null},{"id":"2106.04016","title":"Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering","created":"2021-06-08","cited_by_count":20,"area":null},{"id":"2502.14727","title":"WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models","created":"2025-02-20","cited_by_count":18,"area":"rag"},{"id":"2304.13689","title":"HeySQuAD: A Spoken Question Answering Dataset","created":"2023-04-26","cited_by_count":16,"area":null},{"id":"2112.05842","title":"Revisiting the Boundary between ASR and NLU in the Age of Conversational Dialog Systems","created":"2021-12-10","cited_by_count":15,"area":null},{"id":"2203.04911","title":"DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering","created":"2022-03-09","cited_by_count":15,"area":null},{"id":"2308.10390","title":"LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models","created":"2023-08-20","cited_by_count":14,"area":null},{"id":"2412.16500","title":"Speech Retrieval-Augmented Generation without Automatic Speech Recognition","created":"2024-12-21","cited_by_count":14,"area":"rag"},{"id":"2401.13463","title":"SpeechDPR: End-to-End Spoken Passage Retrieval for Open-Domain Spoken Question Answering","created":"2024-01-24","cited_by_count":12,"area":null},{"id":"2409.10999","title":"Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models","created":"2024-09-17","cited_by_count":10,"area":null},{"id":"2312.09781","title":"GSQA: An End-to-End Model for Generative Spoken Question Answering","created":"2023-12-15","cited_by_count":9,"area":null},{"id":"2406.10083","title":"On the Evaluation of Speech Foundation Models for Spoken Language Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2401.02921","title":"Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks","created":"2024-01-05","cited_by_count":8,"area":null},{"id":"2412.09818","title":"MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models","created":"2024-12-13","cited_by_count":8,"area":"lr"},{"id":"2412.15712","title":"Contrastive Learning for Task-Independent SpeechLLM-Pretraining","created":"2024-12-20","cited_by_count":8,"area":null},{"id":"2505.19163","title":"SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs","created":"2025-05-25","cited_by_count":8,"area":null},{"id":"2602.24195","title":"Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume","created":"2026-02-27","cited_by_count":8,"area":"mllm"},{"id":"2502.13645","title":"Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks","created":"2025-02-19","cited_by_count":7,"area":null},{"id":"2601.02391","title":"WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables","created":"2025-12-25","cited_by_count":7,"area":null},{"id":"2209.12944","title":"On the Impact of Speech Recognition Errors in Passage Retrieval for Spoken Question Answering","created":"2022-09-26","cited_by_count":6,"area":null},{"id":"2502.05389","title":"The Role of Prosody in Spoken Question Answering","created":"2025-02-08","cited_by_count":6,"area":null},{"id":"2209.00277","title":"Video-Guided Curriculum Learning for Spoken Video Grounding","created":"2022-09-01","cited_by_count":5,"area":null},{"id":"2506.01808","title":"NAVER LABS Europe Submission to the Instruction-following Track","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2305.08502","title":"MeeQA: Natural Questions in Meeting Transcripts","created":"2023-05-15","cited_by_count":4,"area":null},{"id":"2305.09652","title":"The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation","created":"2023-05-16","cited_by_count":4,"area":null},{"id":"2406.09618","title":"Multi-Modal Retrieval For Large Language Model Based Speech Recognition","created":"2024-06-13","cited_by_count":4,"area":"mllm"},{"id":"2505.13036","title":"KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 2025","created":"2025-05-19","cited_by_count":4,"area":null},{"id":"2505.16774","title":"IFEval-Audio: Benchmarking Instruction-Following Capability in Audio-based Large Language Models","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2601.20417","title":"SpeechMapper: Speech-to-text Embedding Projector for LLMs","created":"2026-01-28","cited_by_count":4,"area":null},{"id":"2408.14595","title":"Surprisingly Fragile: Assessing and Addressing Prompt Instability in Multimodal Foundation Models","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2412.15995","title":"Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modeling","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2502.16942","title":"NUTSHELL: A Dataset for Abstract Generation from Scientific Talks","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2204.13496","title":"EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification","created":"2022-04-28","cited_by_count":2,"area":null},{"id":"2212.03866","title":"Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task","created":"2022-12-07","cited_by_count":2,"area":null},{"id":"2406.05876","title":"Zero-Shot End-To-End Spoken Question Answering In Medical Domain","created":"2024-06-09","cited_by_count":2,"area":null},{"id":"2409.06635","title":"MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2409.13483","title":"A Multimodal Dense Retrieval Approach for Speech-Based Open-Domain Question Answering","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2510.07890","title":"Standard-to-Dialect Transfer Trends Differ across Text and Speech: A Case Study on Intent and Topic Classification in German Dialects","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2511.09282","title":"End-to-end Contrastive Language-Speech Pretraining Model For Long-form Spoken Question Answering","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2601.03262","title":"Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey","created":"2025-12-16","cited_by_count":2,"area":"rag"},{"id":"2107.04691","title":"An Initial Investigation of Non-Native Spoken Question-Answering","created":"2021-07-09","cited_by_count":1,"area":null},{"id":"2402.02655","title":"VlogQA: Task, Dataset, and Baseline Models for Vietnamese Spoken-Based Machine Reading Comprehension","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2505.23308","title":"Spoken question answering for visual queries","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2605.03361","title":"ReasonAudio: A Benchmark for Evaluating Reasoning Beyond Matching in Text-Audio Retrieval","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2606.01016","title":"PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2306.08667","title":"When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2506.17019","title":"Instituto de Telecomunica\\c{c}\\~oes at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2510.20193","title":"Multimedia-Aware Question Answering: A Review of Retrieval and Cross-Modal Reasoning Architectures","created":"2025-10-23","cited_by_count":0,"area":"rag"},{"id":"2603.16292","title":"Attention-guided Evidence Grounding for Spoken Question Answering","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.27984","title":"KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evaluating SpeechLMs","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2606.00523","title":"ProactiveLLM: Learning Active Interaction for Streaming Large Language Models","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.26396","title":"At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization","created":"2026-06-24","cited_by_count":0,"area":"mechinterp"},{"id":"2608.01881","title":"Hear, Invoke, and Understand: A Skill-Calling Multimodal Agent for Large Audio Language Models","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.03970","title":"Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input Perturbations","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2608.16203","title":"INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.22872","title":"Better Retrieval, Worse Robustness: How Multi-hop RAG Amplifies Upstream ASR Errors","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.24048","title":"Don't Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understanding","created":"2026-08-25","cited_by_count":0,"area":"agents"},{"id":"2608.26194","title":"A Reranker for Orchestrating Heterogeneous Speech and Text Retrievers","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"id":"2608.30475","title":"ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.18521","title":"VoiceTrace: A Benchmark and Retrieval Framework for Who-Said-What Speech Retrieval","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.19879","title":"V\\={a}kQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22214","title":"The Bairong System for MLC-SLM 2026: Dynamic Question-Aware Evidence Routing for Multilingual Conversational Speech Understanding","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.35645","title":"CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37617","title":"AS$^2$D: Accelerating On-Demand Audio Understanding on Mobile Devices","created":"2026-09-29","cited_by_count":0,"area":"inference"},{"id":"2610.00316","title":"DuplexSpeechBench-Document Grounding: Benchmarking Document Grounding and Hallucinations in Voice Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"}],"next_cursor":null}