{"total":34,"rows":[{"id":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200,"area":null},{"id":"2110.06733","title":"Systematic Inequalities in Language Technology Performance across the World's Languages","created":"2021-10-13","cited_by_count":120,"area":null},{"id":"2212.08011","title":"Multi-VALUE: A Framework for Cross-Dialectal English NLP","created":"2022-12-15","cited_by_count":53,"area":null},{"id":"2403.11009","title":"DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages","created":"2024-03-16","cited_by_count":50,"area":null},{"id":"2410.02678","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","created":"2024-10-03","cited_by_count":39,"area":null},{"id":"2112.03497","title":"Dataset Geography: Mapping Language Data to Language Users","created":"2021-12-07","cited_by_count":22,"area":null},{"id":"2304.13689","title":"HeySQuAD: A Spoken Question Answering Dataset","created":"2023-04-26","cited_by_count":16,"area":null},{"id":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","cited_by_count":16,"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":"2211.00922","title":"Dialect-robust Evaluation of Generated Text","created":"2022-11-02","cited_by_count":14,"area":null},{"id":"2510.18915","title":"UNO-Bench: A Unified Benchmark for Exploring the Compositional Law Between Uni-modal and Omni-modal in Omni Models","created":"2025-10-21","cited_by_count":13,"area":null},{"id":"2205.02364","title":"KenSwQuAD -- A Question Answering Dataset for Swahili Low Resource Language","created":"2022-05-04","cited_by_count":12,"area":null},{"id":"2411.10954","title":"Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties","created":"2024-11-17","cited_by_count":12,"area":null},{"id":"2305.14716","title":"GlobalBench: A Benchmark for Global Progress in Natural Language Processing","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2509.20045","title":"Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks","created":"2025-09-24","cited_by_count":9,"area":null},{"id":"2502.15919","title":"Mind the Gap! Static and Interactive Evaluations of Large Audio Models","created":"2025-02-21","cited_by_count":8,"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":"2603.17837","title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","created":"2026-03-18","cited_by_count":6,"area":null},{"id":"2508.07295","title":"CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation","created":"2025-08-10","cited_by_count":5,"area":null},{"id":"2505.17417","title":"Speechless: Speech Instruction Training Without Speech for Low Resource Languages","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2505.20875","title":"Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2606.05121","title":"Audio Interaction Model","created":"2026-06-03","cited_by_count":4,"area":null},{"id":"2203.09632","title":"Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languages","created":"2022-03-17","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":"2605.12034","title":"Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2603.14782","title":"Information Asymmetry across Language Varieties: A Case Study on Cantonese-Mandarin and Bavarian-German QA","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2606.11033","title":"AuRA: Internalizing Audio Understanding into LLMs as LoRA","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2212.08946","title":"Towards leveraging latent knowledge and Dialogue context for real-world conversational question answering","created":"2022-12-17","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":"2609.11892","title":"Nuha-Speech: Building General-Purpose Arabic Speech-LLMs","created":"2026-09-10","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":"2610.13550","title":"Personalization Without Stereotyping: Do Speech LLMs Know When to Turn a Deaf Ear?","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.17124","title":"D2: High-Capability Full-Duplex Spoken Language Models from Half-Duplex Backbones","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}