{"total":20,"rows":[{"id":"2605.27772","title":"Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox","created":"2026-05-26","cited_by_count":7,"area":null},{"id":"2602.11488","title":"When Audio-LLMs Don't Listen: A Cross-Linguistic Study of Modality Arbitration","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2602.17598","title":"The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\\rightarrow$LLM Pipelines?","created":"2026-02-19","cited_by_count":5,"area":null},{"id":"2604.06138","title":"Generating Synthetic Doctor-Patient Conversations for Long-form Audio Summarization","created":"2026-04-07","cited_by_count":4,"area":null},{"id":"2606.26083","title":"Real-Time Voice AI Hears but Does Not Listen","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2607.13477","title":"Auditing Protocol-Level Shortcuts in Large Audio Language Model Judges for Speech Evaluation","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2608.19515","title":"Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2606.25990","title":"SpeechEQ: Benchmarking Emotional Intelligence Quotient in Socially Aware Voice Conversational Models","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2608.06409","title":"Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.06718","title":"Do Audio Language Models Use Paralinguistic Evidence? Counterfactual Audits for Response Evaluation","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2609.16582","title":"CLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2511.04914","title":"MERaLiON-SER: Robust Speech Emotion Recognition Model for English and SEA Languages","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2606.22473","title":"Interleaved Speech Language Models Latently Work In Text","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2607.11801","title":"Encoder-Side Neuron Identification and Amplification for Acoustic Perception in Large Audio-Language Models","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.17102","title":"Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.05871","title":"Where Does the Sound Go? Tracing Acoustic Information Loss in Audio-Conditioned LLMs","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.26823","title":"Text Scores Do Not Establish Performance on Lexically Non-Diagnostic Speech Tasks: A Qwen2-Audio Quantization Case Study","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.35922","title":"Almost Human, Except When It Matters: VoxParity and the Decisions a Voice Should Change","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38182","title":"EmAvatar: Multimodal Empathetic Response Generation via Conflict Resolution and Expressive Guidance","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2610.08085","title":"DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMs","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}