Related papers: AudioJudge: Understanding What Works in Large Audi…

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…

Voice assistants increasingly rely on Speech Language Models (SpeechLMs) to interpret spoken queries and execute complex tasks, yet existing benchmarks lack domain breadth, acoustic diversity, and compositional reasoning complexity to…

Large Audio Language Models (LALMs), which couple acoustic perception with large language models (LLMs) to extract and understand diverse information from audio, have attracted intense interest from both academic and industrial communities.…

Warning: This paper may contain texts with uncomfortable content. Large Language Models (LLMs) have achieved remarkable performance in various tasks, including those involving multimodal data like speech. However, these models often exhibit…

Large language models (LLMs) can serve as judges that offer rapid and reliable assessments of other LLM outputs. However, models may systematically assign overly favorable ratings to their own outputs, a phenomenon known as self-bias, which…

Current evaluation methods for large language models (LLMs) primarily rely on static benchmarks, presenting two major challenges: limited knowledge coverage and fixed difficulties that mismatch with the evaluated LLMs. These limitations…

Legal judgment prediction is essential for enhancing judicial efficiency. In this work, we identify that existing large language models (LLMs) underperform in this domain due to challenges in understanding case complexities and…

Auscultation is a vital diagnostic tool, yet its utility is often limited by subjective interpretation. While general-purpose Audio-Language Models (ALMs) excel in general domains, they struggle with the nuances of physiological signals. We…

Despite the parallel challenges that audio and text domains face in evaluating generative model outputs, preference learning remains remarkably underexplored in audio applications. Through a PRISMA-guided systematic review of approximately…

Recent multi-modal audio-language models (ALMs) excel at text-audio retrieval but struggle with frame-wise audio understanding. Prior works use temporal-aware labels or unsupervised training to improve frame-wise capabilities, but they…

Large Language Models (LLMs) have recently shown remarkable ability to process not only text but also multimodal inputs such as speech and audio. However, most existing models primarily focus on analyzing input signals using text…

Large Audio-Language Models (LALMs) have recently shown impressive progress in speech recognition, audio captioning, and auditory question answering. Yet, whether these models can perceive spatial dynamics, particularly the motion of sound…

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)…

While large language models have demonstrated impressive reasoning abilities, their extension to the audio modality, particularly within large audio-language models (LALMs), remains underexplored. Addressing this gap requires a systematic…

Existing approaches for aligning large language models with human preferences face a trade-off that requires a separate reward model (RM) for on-policy learning. In this paper, we present a novel alignment framework, SELF-JUDGE that (1)…

Recent literature uses language to build foundation models for audio. These Audio-Language Models (ALMs) are trained on a vast number of audio-text pairs and show remarkable performance in tasks including Text-to-Audio Retrieval,…

How does textual representation of audio relate to the Large Language Model's (LLMs) learning about the audio world? This research investigates the extent to which LLMs can be prompted to generate audio, despite their primary training in…

Speech understanding is essential for interpreting the diverse forms of information embedded in spoken language, including linguistic, paralinguistic, and non-linguistic cues that are vital for effective human-computer interaction. The…

We present "AutoJudge", an automated evaluation method for conversational dialogue systems. The method works by first generating dialogues based on self-talk, i.e. dialogue systems talking to itself. Then, it uses human ratings on these…

Large language models (LLMs) have demonstrated strong instruction-following capabilities in text-based tasks. However, this ability often deteriorates in multimodal models after alignment with non-text modalities such as images or audio.…