{"list":"other","total":64,"rows":[{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2403.20330","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","created":"2024-03-29","cited_by_count":914},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310},{"id":"1805.01042","title":"Hypothesis Only Baselines in Natural Language Inference","created":"2018-05-02","cited_by_count":295},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288},{"id":"2307.09009","title":"How is ChatGPT's behavior changing over time?","created":"2023-07-18","cited_by_count":270},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220},{"id":"2411.00640","title":"Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations","created":"2024-11-01","cited_by_count":148},{"id":"2601.15621","title":"Qwen3-TTS Technical Report","created":"2026-01-22","cited_by_count":118},{"id":"2412.04604","title":"ARC Prize 2024: Technical Report","created":"2024-12-05","cited_by_count":104},{"id":"2506.04779","title":"MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark","created":"2025-06-05","cited_by_count":103},{"id":"2106.00545","title":"Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests","created":"2021-05-31","cited_by_count":77},{"id":"2508.13992","title":"MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence","created":"2025-08-19","cited_by_count":61},{"id":"2604.04847","title":"Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency","created":"2026-04-06","cited_by_count":37},{"id":"2603.13686","title":"$\\tau$-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains","created":"2026-03-14","cited_by_count":36},{"id":"2503.05731","title":"AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons","created":"2025-02-19","cited_by_count":35},{"id":"2510.10444","title":"Do Audio LLMs Really LISTEN, or Just Transcribe? Measuring Lexical vs. Acoustic Emotion Cues Reliance","created":"2025-10-12","cited_by_count":24},{"id":"2510.07978","title":"VoiceAgentBench: Are Voice Assistants ready for agentic tasks?","created":"2025-10-09","cited_by_count":19},{"id":"2510.22758","title":"EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models","created":"2025-10-26","cited_by_count":11},{"id":"2509.16589","title":"Benchmarking Contextual and Paralinguistic Reasoning in Speech-LLMs: A Case Study with In-the-Wild Data","created":"2025-09-20","cited_by_count":10},{"id":"2604.22821","title":"Audio2Tool: Speak, Call, Act -- A Dataset for Benchmarking Speech Tool Use","created":"2026-04-17","cited_by_count":9},{"id":"2604.14548","title":"VoxSafeBench: Not Just What Is Said, but Who, How, and Where","created":"2026-04-16","cited_by_count":8},{"id":"2507.10859","title":"MultiVox: A Benchmark for Evaluating Voice Assistants for Multimodal Interactions","created":"2025-07-14","cited_by_count":7},{"id":"2601.19956","title":"VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models","created":"2026-01-27","cited_by_count":7},{"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},{"id":"2607.27453","title":"VAmoS Bench: Voice Agent Simulation Bench","created":"2026-07-29","cited_by_count":7},{"id":"2606.10581","title":"ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models","created":"2026-06-09","cited_by_count":6},{"id":"2604.15037","title":"From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench","created":"2026-04-16","cited_by_count":4},{"id":"2609.21967","title":"NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities","created":"2026-09-18","cited_by_count":4},{"id":"2609.24812","title":"MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agents","created":"2026-09-21","cited_by_count":4},{"id":"2512.16832","title":"What Do Prosody and Text Convey? Characterizing How Meaningful Information is Distributed Across Multiple Channels","created":"2025-12-18","cited_by_count":3},{"id":"2609.14005","title":"StepAudio 3 Realtime Technical Report","created":"2026-09-12","cited_by_count":3},{"id":"2609.20152","title":"MTVA-Bench: Evaluating the Language Model Inside Cascaded Voice Agents","created":"2026-09-17","cited_by_count":3},{"id":"2603.16941","title":"The Voice Behind the Words: Quantifying Intersectional Bias in SpeechLLMs","created":"2026-03-15","cited_by_count":2},{"id":"2606.26083","title":"Real-Time Voice AI Hears but Does Not Listen","created":"2026-06-24","cited_by_count":2},{"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},{"id":"2607.14846","title":"RW-Voice-EQ Bench: A Real World Benchmark for Evaluating Voice AI Systems","created":"2026-07-16","cited_by_count":2},{"id":"2608.19515","title":"Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does","created":"2026-08-20","cited_by_count":2},{"id":"2609.00727","title":"Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models","created":"2026-09-01","cited_by_count":2},{"id":"2609.13076","title":"MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant","created":"2026-09-11","cited_by_count":2},{"id":"2609.17360","title":"Same Words, Different Actions: Paired Turn-Taking Evaluation under Rewritten Dialogue Contexts","created":"2026-09-15","cited_by_count":2},{"id":"2609.19334","title":"A frontend-backend architecture for tool calls in full-duplex speech models","created":"2026-09-16","cited_by_count":2},{"id":"2609.25611","title":"Qwen3.8-Omni: Towards Native Omni-Modal Agents","created":"2026-09-22","cited_by_count":2},{"id":"2606.06168","title":"ProSarc: Prosody-Aware Sarcasm Recognition Framework via Temporal Prosodic Incongruity","created":"2026-06-04","cited_by_count":1},{"id":"2608.03054","title":"Towards More Expressive Spoken LLMs: Fine-Grained Intent Benchmarking and Acoustic-Lexical Decoupled Policy Optimization","created":"2026-08-04","cited_by_count":1},{"id":"2608.06718","title":"Do Audio Language Models Use Paralinguistic Evidence? Counterfactual Audits for Response Evaluation","created":"2026-08-07","cited_by_count":1},{"id":"2608.09189","title":"EmoS: A Theory-Grounded Framework for Evaluating and Aligning Emotional Intelligence in Spoken Language Models","created":"2026-08-10","cited_by_count":1},{"id":"2608.19211","title":"Represented but Ignored: A Causal Account of Prosodic Underuse in Audio-Language Models","created":"2026-06-12","cited_by_count":1},{"id":"2609.00570","title":"VoiceLongMemEval: Do Assistants Remember How You Sounded?","created":"2026-09-01","cited_by_count":1},{"id":"2609.09263","title":"Voice or Stereotype? Disentangling Acoustic and Content-Based Gender in Speech-to-Speech Models","created":"2026-09-08","cited_by_count":1},{"id":"2609.16582","title":"CLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection","created":"2026-09-15","cited_by_count":1},{"id":"2609.19596","title":"Full-Duplex Speech Models Take the Floor When Asked, Not When Needed","created":"2026-09-17","cited_by_count":1},{"id":"2609.21183","title":"I'll Keep an Ear Out: Teaching AudioLLMs Proactive Audio Assistance","created":"2026-09-18","cited_by_count":1},{"id":"2609.22135","title":"Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models","created":"2026-08-24","cited_by_count":1},{"id":"2609.23462","title":"Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge","created":"2026-09-20","cited_by_count":1},{"id":"2609.25176","title":"Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction","created":"2026-09-21","cited_by_count":1},{"id":"2609.29287","title":"AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks","created":"2026-09-24","cited_by_count":1},{"id":"2609.29452","title":"Voice Agents under Acoustic Stress: From Signal Degradation to Interaction and Action","created":"2026-09-24","cited_by_count":1}],"next_cursor":null}