相关论文: Extracting and Steering Emotion Representations in…

We show that emotion vectors in LLMs are organized by a two-dimensional valence-arousal (VA) subspace exhibiting circular geometry. Through principal component decomposition and ridge regression, we recover meaningful VA axes underlying…

Multimodal large language models (MLLMs) have been widely applied across various fields due to their powerful perceptual and reasoning capabilities. In the realm of psychology, these models hold promise for a deeper understanding of human…

Emotion recognition based on body movements is vital in human-computer interaction. However, existing emotion recognition methods predominantly focus on enhancing classification accuracy, often neglecting the provision of textual…

Emotion recognition from electroencephalography (EEG) signals remains challenging due to high inter-subject variability, limited labeled data, and the lack of interpretable reasoning in existing approaches. While recent multimodal large…

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…

Gaps arise between a language model's use of concepts and people's expectations. This gap is critical when LLMs generate text to help people communicate via Augmentative and Alternative Communication (AAC) tools. In this work, we introduce…

Existing behavioral alignment techniques for Large Language Models (LLMs) often neglect the discrepancy between surface compliance and internal unaligned representations, leaving LLMs vulnerable to long-tail risks. More crucially, we posit…

Emotion is a core paralinguistic feature in voice interaction. It is widely believed that emotion understanding models learn fundamental representations that transfer to synthesized speech, making emotion understanding results a plausible…

Large language models (LLMs) have revolutionized algorithm development, yet their application in symbolic regression, where algorithms automatically discover symbolic expressions from data, remains limited. In this paper, we propose a…

The rapid advancement of large language models (LLMs) has made machine-generated text increasingly difficult to distinguish from human-written text. While recent studies explore leveraging internal representations of language models to…

Extracting clinical information from medical transcripts in low-resource languages remains a significant challenge in healthcare natural language processing (NLP). This study evaluates a two-step pipeline combining Aya-expanse-8B as a…

It is a critical challenge to efficiently unlock the powerful reasoning potential of Large Language Models (LLMs) for specific tasks or new distributions. Existing test-time adaptation methods often require tuning model parameters, which is…

Psychotherapy is a primary treatment for many mental health conditions, yet the interplay among therapist behaviors, client responses, and the therapeutic relationship remains difficult to untangle. This work advances a computational…

Emotion classification in multilingual settings remains constrained by the scarcity of annotated data: existing corpora are predominantly English, single-label, and cover few languages. We address this gap by constructing a large-scale…

Alignment safety research assumes that ethical instructions improve model behavior, but how language models internally process such instructions remains unknown. We conducted over 600 multi-agent simulations across four models (Llama 3.3…

The mechanisms by which reasoning training reshapes LLMs' internal computations remain unclear. We study lightweight steering vectors inserted into the base model's residual stream and trained with a reinforcement-learning objective. These…

Standard classification models often map inputs directly to labels without explicit reasoning, potentially limiting their performance, robustness, and interpretability. This paper introduces a novel two-stage approach to enhance text…

This study introduces a novel method for irony detection, applying Large Language Models (LLMs) with prompt-based learning to facilitate emotion-centric text augmentation. Traditional irony detection techniques typically fall short due to…

Speech Self-Supervised Learning (SSL) has demonstrated considerable efficacy in various downstream tasks. Nevertheless, prevailing self-supervised models often overlook the incorporation of emotion-related prior information, thereby…

Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased." This binary framing misses the gradual,…