中文
相关论文

相关论文: Investigating Faithfulness in Large Audio Language…

200 篇论文

Large Audio-Language Models (LALMs) have demonstrated remarkable performance in tasks involving audio perception and understanding, such as speech recognition and audio captioning. However, their reasoning capabilities - critical for…

声音 · 计算机科学 2025-01-14 Ziyang Ma , Zhuo Chen , Yuping Wang , Eng Siong Chng , Xie Chen

Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question, but it is unclear if the stated reasoning is a faithful explanation of the model's actual reasoning…

As Large Language Models (LLMs) are increasingly being employed in real-world applications in critical domains such as healthcare, it is important to ensure that the Chain-of-Thought (CoT) reasoning generated by these models faithfully…

计算与语言 · 计算机科学 2024-07-02 Sree Harsha Tanneru , Dan Ley , Chirag Agarwal , Himabindu Lakkaraju

The foundational capabilities established by Large Language Models (LLMs) have paved the way for Multimodal Large Language Models (MLLMs), within which Large Audio Language Models (LALMs) are essential for realizing universal auditory…

Recent advancements in large audio language models (LALMs) have demonstrated impressive results and promising prospects in universal understanding and reasoning across speech, music, and general sound. However, these models still lack the…

Chain-of-thought (CoT) reasoning enhances performance of large language models, but questions remain about whether these reasoning traces faithfully reflect the internal processes of the model. We present the first comprehensive study of…

计算与语言 · 计算机科学 2025-11-04 Sriram Balasubramanian , Samyadeep Basu , Soheil Feizi

Large language models (LLMs) increasingly rely on Chain-of-Thought (CoT) prompting to improve problem-solving and provide seemingly transparent explanations. However, growing evidence shows that CoT often fail to faithfully represent the…

人工智能 · 计算机科学 2026-03-03 Xu Shen , Song Wang , Zhen Tan , Laura Yao , Xinyu Zhao , Kaidi Xu , Xin Wang , Tianlong Chen

Closed-source large language models (LLMs), such as ChatGPT and Gemini, are increasingly consulted for medical advice, yet their explanations may appear plausible while failing to reflect the model's underlying reasoning process. This gap…

With advancements in large audio-language models (LALMs), which enhance large language models (LLMs) with auditory capabilities, these models are expected to demonstrate universal proficiency across various auditory tasks. While numerous…

音频与语音处理 · 电气工程与系统科学 2026-04-28 Chih-Kai Yang , Neo S. Ho , Hung-yi Lee

Recent Large Audio-Language Models (LALMs) have shown strong performance on various audio understanding tasks such as speech translation and Audio Q\&A. However, they exhibit significant limitations on challenging audio reasoning tasks in…

计算与语言 · 计算机科学 2025-09-29 Zhen Xiong , Yujun Cai , Zhecheng Li , Junsong Yuan , Yiwei Wang

Recent advancements in large audio-language models (LALMs) have shown impressive capabilities in understanding and reasoning about audio and speech information. However, these models still face challenges, including hallucinating…

音频与语音处理 · 电气工程与系统科学 2025-01-03 Chun-Yi Kuan , Hung-yi Lee

Recent advances in reasoning models have driven significant progress in text and multimodal domains, yet audio reasoning remains relatively limited. Only a few Large Audio Language Models (LALMs) incorporate explicit Chain-of-Thought (CoT)…

音频与语音处理 · 电气工程与系统科学 2026-04-21 Longhao Li , Hongjie Chen , Zehan Li , Qihan Hu , Jian Kang , Jie Li , Lei Xie , Yongxiang Li

Large audio language models (LALMs) leverage multimodal representations to generate open-ended answers to natural language queries about audio. In this paper, we (1) provide empirical evidence that assessment of LALMs using the popular…

声音 · 计算机科学 2026-05-28 Daniel Chenyu Lin , Michael Freeman , John Thickstun

Large Audio Language Models (LALMs), powered by the chain-of-thought (CoT) paradigm, have shown remarkable reasoning capabilities. Intuitively, different problems often require varying depths of reasoning. While some methods can determine…

机器学习 · 计算机科学 2025-11-20 Zhichao Sheng , Shilin Zhou , Chen Gong , Zhenghua Li

Understanding the extent to which Chain-of-Thought (CoT) generations align with a large language model's (LLM) internal computations is critical for deciding whether to trust an LLM's output. As a proxy for CoT faithfulness, Lanham et al.…

计算与语言 · 计算机科学 2024-06-24 Oliver Bentham , Nathan Stringham , Ana Marasović

Recent advances in large audio language models (LALMs) have primarily been assessed using a multiple-choice question answering (MCQA) framework. However, subtle changes, such as shifting the order of choices, result in substantially…

计算与语言 · 计算机科学 2025-10-07 Fernando López , Santosh Kesiraju , Jordi Luque

Large reasoning models (LRMs) increasingly rely on step-by-step Chain-of-Thought (CoT) reasoning to improve task performance, particularly in high-resource languages such as English. While recent work has examined final-answer accuracy in…

计算与语言 · 计算机科学 2025-10-13 Raoyuan Zhao , Yihong Liu , Hinrich Schütze , Michael A. Hedderich

Audio Language Models (ALMs) have recently shown strong capabilities in unified reasoning over speech, sound, and natural language; yet they inherit behavioral issues observed in Large Language Models, including sycophancy--the tendency to…

Large Audio-Language Models (LALMs) are increasingly deployed in real-world applications, yet their robustness against malicious audio injection attacks remains underexplored. This study systematically evaluates five leading LALMs across…

计算与语言 · 计算机科学 2025-07-11 Guanyu Hou , Jiaming He , Yinhang Zhou , Ji Guo , Yitong Qiao , Rui Zhang , Wenbo Jiang

Large audio-language models (LALMs) enhance traditional large language models by integrating audio perception capabilities, allowing them to tackle audio-related tasks. Previous research has primarily focused on assessing the performance of…

音频与语音处理 · 电气工程与系统科学 2024-06-13 Chun-Yi Kuan , Wei-Ping Huang , Hung-yi Lee
‹ 上一页 1 2 3 10 下一页 ›