Related papers: Shared Emotion Geometry Across Small Language Mode…
Accurate emotion understanding in videos necessitates effectively recognizing and interpreting emotional states by integrating visual, textual, auditory, and contextual cues. Although recent Large Multimodal Models (LMMs) have exhibited…
I study whether emotionally framed evaluation follow-ups change both the behavior and the calm-relative internal representations of small, locally deployed language models. Our main benchmark uses Qwen 3.5 0.8B on four impossible-constraint…
We investigate feature universality in Gemma-2 language models (Gemma-2-2B and Gemma-2-9B), asking whether models with a four-fold difference in scale still converge on comparable internal concepts. Using the Sparse Autoencoder (SAE)…
Large language models (LLMs) and their variants have shown extraordinary efficacy across numerous downstream natural language processing (NLP) tasks, which has presented a new vision for the development of NLP. Despite their remarkable…
Large Language Models (LLMs) demonstrate remarkable capabilities in text generation, yet their emotional consistency and semantic coherence in social media contexts remain insufficiently understood. This study investigates how LLMs handle…
Large language models are increasingly used as behavioral simulators, but it remains unclear when their outputs reflect human-like cognitive mechanisms rather than prompt-sensitive surface patterns. We study this question through the…
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…
Despite significant progress in transformer interpretability, an understanding of the computational mechanisms of large language models (LLMs) remains a fundamental challenge. Many approaches interpret a network's hidden representations but…
We investigate whether independently trained language models converge to geometrically compatible latent representations, and whether this compatibility can be exploited to correct model behavior at inference time without any weight…
Large Language Models (LLMs) demonstrate increasing conversational fluency, yet instilling them with nuanced, human-like emotional expression remains a significant challenge. Current alignment techniques often address surface-level output…
Large Language Models (LLMs) often display overconfidence, presenting information with unwarranted certainty in high-stakes contexts. We investigate the internal basis of this behavior via mechanistic interpretability. Using open-sourced…
Understanding the emotions in a dialogue usually requires external knowledge to accurately understand the contents. As the LLMs become more and more powerful, we do not want to settle on the limited ability of the pre-trained language…
Emotions are experienced and expressed differently across the world. In order to use Large Language Models (LMs) for multilingual tasks that require emotional sensitivity, LMs must reflect this cultural variation in emotion. In this study,…
Hidden states change substantially across the layers of modern language models, but most layer-wise analyses focus on one aspect of that change. We propose Layer-wise Representation Dynamics (LRD), a framework with three layer-wise…
Large language models (LLMs) reflect societal norms and biases, especially about gender. While societal biases and stereotypes have been extensively researched in various NLP applications, there is a surprising gap for emotion analysis.…
Multimodal emotion understanding requires effective integration of text, audio, and visual modalities for both discrete emotion recognition and continuous sentiment analysis. We present EGMF, a unified framework combining expert-guided…
Fine-tuning Large Language Models (LLMs) remains structurally uncertain despite parameter-efficient methods such as Low-Rank Adaptation (LoRA), as the layer-specific roles of internal representations are poorly understood, leading to…
Preserving affective nuance remains a challenge in Machine Translation (MT), where semantic equivalence often takes precedence over emotional fidelity. This paper evaluates the performance of three state-of-the-art Small Language Models…
The ability to represent emotion plays a significant role in human cognition and social interaction, yet the high-dimensional geometry of this affective space and its neural underpinnings remain debated. A key challenge, the…
The geometric evolution of token representations in large language models (LLMs) presents a fundamental paradox: while human language inherently organizes semantic information in low-dimensional spaces ($\sim 10^1$ dimensions), modern LLMs…