相关论文: Negative Before Positive: Asymmetric Valence Proce…

Vision-Language Models (VLMs) have demonstrated remarkable performance across a variety of real-world tasks. However, existing VLMs typically process visual information by serializing images, a method that diverges significantly from the…

Convolutional neural networks have been successfully applied to various NLP tasks. However, it is not obvious whether they model different linguistic patterns such as negation, intensification, and clause compositionality to help the…

Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of internal features in Large Language Models (LLMs). However, a persistent challenge lies in linking such internal features to the reliable…

Computer vision has benefited from initializing multiple deep layers with weights pretrained on large supervised training sets like ImageNet. Natural language processing (NLP) typically sees initialization of only the lowest layer of deep…

Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. Despite exhibiting coherent answers and apparent reasoning behaviors, LLMs rely on…

Large language models (LLMs) have demonstrated impressive capabilities across diverse languages. This study explores how LLMs handle multilingualism. Based on observed language ratio shifts among layers and the relationships between network…

The advancement of Multimodal Large Language Models (MLLMs) has greatly accelerated the development of applications in understanding integrated texts and images. Recent works leverage image-caption datasets to train MLLMs, achieving…

Emotion is a central dimension of spoken communication, yet, we still lack a mechanistic account of how modern large audio-language models (LALMs) encode it internally. We present the first neuron-level interpretability study of…

Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications.…

Large language models appear to develop internal representations of emotion -- "emotion circuits," "emotion neurons," and structured emotional manifolds have been reported across multiple model families. But every study making these claims…

We investigate the robustness of Large Language Models (LLMs) to structural interventions by deleting and swapping adjacent layers during inference. Surprisingly, models retain 72-95% of their original top-1 prediction accuracy without any…

This research aims to unravel how large language models (LLMs) iteratively refine token predictions through internal processing. We utilized a logit lens technique to analyze the model's token predictions derived from intermediate…

Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in comprehending complex visual content. However, the mechanisms underlying how VLMs process visual information remain largely unexplored. In this paper, we…

Large reasoning models (LRMs) achieve strong performance on mathematical reasoning tasks, often attributed to their capability to generate explicit chain-of-thought (CoT) explanations. However, recent work shows that LRMs often arrive at…

Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts. While recent studies suggest that LLMs can transfer skills learned in one language to others, the internal mechanisms behind this…

The analysis of emotions expressed in text has numerous applications. In contrast to categorical analysis, focused on classifying emotions according to a pre-defined set of common classes, dimensional approaches can offer a more nuanced way…

Reasoning-oriented large language models (RLMs) achieve strong gains on tasks such as mathematics and coding by generating explicit intermediate reasoning. However, their impact on machine translation (MT) remains underexplored. We…

This work studies the capabilities of a large language model (LLM) to understand paralinguistic aspects of speech without fine-tuning its weights. We utilize an end-to-end system with a speech encoder, which is trained to produce token…

Subjective language understanding refers to a broad set of natural language processing tasks where the goal is to interpret or generate content that conveys personal feelings, opinions, or figurative meanings rather than objective facts.…

We present a mechanistic interpretability study of GPT-2 that causally examines how sentiment information is processed across its transformer layers. Using systematic activation patching across all 12 layers, we test the hypothesized…