相关论文: Beyond Hidden-Layer Manipulation: Semantically-Awa…

Chain-of-Thought (CoT) reasoning is a critical capability for large language models (LLMs), enabling them to tackle com- plex multi-step tasks. While base LLMs, pre-trained on general text corpora, often struggle with reasoning due to a…

Static analysis is a widely used technique in software engineering for identifying and mitigating bugs. However, a significant hurdle lies in achieving a delicate balance between precision and scalability. Large Language Models (LLMs) offer…

Many recent delineation techniques owe much of their increased effectiveness to path classification algorithms that make it possible to distinguish promising paths from others. The downside of this development is that they require annotated…

Modern face recognition models embed identities on a unit hypersphere, where identity variation forms tight clusters. Conversely, shared semantic attributes can often be effectively approximated as linear directions in the latent space.…

This paper introduces SignAgent, a novel agentic framework that utilises Large Language Models (LLMs) for scalable, linguistically-grounded Sign Language (SL) annotation and dataset curation. Traditional computational methods for SLs often…

Recent advancements in Artificial Intelligence, particularly in Large Language Models (LLMs), have transformed natural language processing by improving generative capabilities. However, detecting biases embedded within these models remains…

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

A recent study (Kuribayashi et al., 2025) has shown that human sentence processing behavior, typically measured on syntactically unchallenging constructions, can be effectively modeled using surprisal from early layers of large language…

Beam search decoding is the de-facto method for decoding auto-regressive Neural Machine Translation (NMT) models, including multilingual NMT where the target language is specified as an input. However, decoding multilingual NMT models…

The rapid advancement of large language models (LLMs) has led to significant improvements in their capabilities, but also to increased concerns about their alignment with human values and intentions. Current alignment strategies, including…

As one of the successful Transformer-based models in computer vision tasks, SegFormer demonstrates superior performance in semantic segmentation. Nevertheless, the high computational cost greatly challenges the deployment of SegFormer on…

This report examines the synergy between Large Language Models (LLMs) and Static Application Security Testing (SAST) to improve vulnerability discovery. Traditional SAST tools, while effective for proactive security, are limited by high…

We present new learning dynamics combining (independent) log-linear learning and value iteration for stochastic games within the auxiliary stage game framework. The dynamics presented provably attain the efficient equilibrium (also known as…

We present new learning dynamics combining (independent) log-linear learning and value iteration for stochastic games within the auxiliary stage game framework. The dynamics presented provably attain the efficient equilibrium (also known as…

Large language models (LLMs) offer an inexpensive yet powerful way to annotate text, but are often inconsistent when compared with experts. These errors can bias downstream estimates of population parameters such as regression coefficients…

The vast size of Large Language Models (LLMs) has prompted a search to optimize inference. One effective approach is dynamic inference, which adapts the architecture to the sample-at-hand to reduce the overall computational cost. We…

While Large Language Models (LLMs) can solve many NLP tasks in zero-shot settings, applications involving embodied agents remain problematic. In particular, complex plans that require multi-step reasoning become difficult and too costly as…

Modern recommender systems struggle to effectively utilize the rich, yet high-dimensional and noisy, multi-modal features generated by Large Language Models (LLMs). Treating these features as static inputs decouples them from the core…

Current developments in large language models (LLMs) have enabled impressive zero-shot capabilities across various natural language tasks. An interesting application of these systems is in the automated assessment of natural language…

Large language model agents increasingly rely on external skills to solve complex tasks, where skills act as modular units that extend their capabilities beyond what parametric memory alone supports. Existing methods assume external skills…