{"list":"other","total":67,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"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":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"2006.13979","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","created":"2020-06-24","cited_by_count":501},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220},{"id":"2305.10790","title":"Listen, Think, and Understand","created":"2023-05-18","cited_by_count":209},{"id":"2402.16837","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","created":"2024-02-26","cited_by_count":169},{"id":"2211.03929","title":"Comparative layer-wise analysis of self-supervised speech models","created":"2022-11-08","cited_by_count":158},{"id":"2406.11768","title":"GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities","created":"2024-06-17","cited_by_count":156},{"id":"2110.01900","title":"DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT","created":"2021-10-05","cited_by_count":144},{"id":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128},{"id":"2402.16438","title":"Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models","created":"2024-02-26","cited_by_count":126},{"id":"2410.07149","title":"Towards Interpreting Visual Information Processing in Vision-Language Models","created":"2024-10-09","cited_by_count":122},{"id":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109},{"id":"2410.02762","title":"Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations","created":"2024-10-03","cited_by_count":104},{"id":"2011.11588","title":"The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","created":"2020-11-23","cited_by_count":101},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100},{"id":"2305.16130","title":"Language Models Implement Simple Word2Vec-style Vector Arithmetic","created":"2023-05-25","cited_by_count":98},{"id":"2303.09435","title":"Jump to Conclusions: Short-Cutting Transformers With Linear Transformations","created":"2023-03-16","cited_by_count":90},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78},{"id":"2406.12775","title":"Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries","created":"2024-06-18","cited_by_count":78},{"id":"2203.06849","title":"SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities","created":"2022-03-14","cited_by_count":77},{"id":"2305.10615","title":"ML-SUPERB: Multilingual Speech Universal PERformance Benchmark","created":"2023-05-18","cited_by_count":71},{"id":"2406.08619","title":"Self-Supervised Speech Representations are More Phonetic than Semantic","created":"2024-06-12","cited_by_count":71},{"id":"2411.05361","title":"Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks","created":"2024-11-08","cited_by_count":71},{"id":"2406.13340","title":"SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words","created":"2024-06-19","cited_by_count":68},{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64},{"id":"2410.12787","title":"The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio","created":"2024-10-16","cited_by_count":53},{"id":"2409.20007","title":"DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data","created":"2024-09-30","cited_by_count":45},{"id":"2505.13237","title":"SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information","created":"2025-05-19","cited_by_count":42},{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39},{"id":"2306.10548","title":"MARBLE: Music Audio Representation Benchmark for Universal Evaluation","created":"2023-06-18","cited_by_count":38},{"id":"2312.12141","title":"Neuron-Level Knowledge Attribution in Large Language Models","created":"2023-12-19","cited_by_count":37},{"id":"2406.03872","title":"BLSP-Emo: Towards Empathetic Large Speech-Language Models","created":"2024-06-06","cited_by_count":36},{"id":"2406.18871","title":"DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment","created":"2024-06-27","cited_by_count":33},{"id":"2410.16130","title":"Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning","created":"2024-10-21","cited_by_count":31},{"id":"2407.09886","title":"Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation","created":"2024-07-13","cited_by_count":27},{"id":"2406.11193","title":"MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model","created":"2024-06-17","cited_by_count":26},{"id":"2502.10835","title":"Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models","created":"2025-02-15","cited_by_count":23},{"id":"2503.11667","title":"LogitLens4LLMs: Extending Logit Lens Analysis to Modern Large Language Models","created":"2025-02-24","cited_by_count":23},{"id":"2407.06957","title":"Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models","created":"2024-07-09","cited_by_count":21},{"id":"2406.05065","title":"Emo-bias: A Large Scale Evaluation of Social Bias on Speech Emotion Recognition","created":"2024-06-07","cited_by_count":20},{"id":"2406.12288","title":"An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs","created":"2024-06-18","cited_by_count":20},{"id":"2211.09511","title":"Hey ASR System! Why Aren't You More Inclusive? Automatic Speech Recognition Systems' Bias and Proposed Bias Mitigation Techniques. A Literature Review","created":"2022-11-17","cited_by_count":19},{"id":"2502.09940","title":"A Preliminary Exploration with GPT-4o Voice Mode","created":"2025-02-14","cited_by_count":16},{"id":"2401.00273","title":"Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision","created":"2023-12-30","cited_by_count":13},{"id":"2310.03018","title":"Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages","created":"2023-10-04","cited_by_count":12},{"id":"2310.14928","title":"Unveiling A Core Linguistic Region in Large Language Models","created":"2023-10-23","cited_by_count":12},{"id":"2406.05806","title":"Do Prompts Really Prompt? Exploring the Prompt Understanding Capability of Whisper","created":"2024-06-09","cited_by_count":12},{"id":"2406.16990","title":"AND: Audio Network Dissection for Interpreting Deep Acoustic Models","created":"2024-06-24","cited_by_count":7},{"id":"2409.05910","title":"Property Neurons in Self-Supervised Speech Transformers","created":"2024-09-07","cited_by_count":5}],"next_cursor":null}