相关论文: Visualizing token importance for black-box languag…

In this paper, we investigate the phenomena of "selection biases" in Large Language Models (LLMs), focusing on problems where models are tasked with choosing the optimal option from an ordered sequence. We delve into biases related to…

Large language models (LLMs) have demonstrated impressive performance across various domains. However, for clinical diagnosis, higher expectations are required for LLM's reliability and sensitivity: thinking like physicians and remaining…

As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) safety workflow, evaluation, diagnosis, and alignment are…

Currently many benchmarks have been proposed to evaluate the perception ability of the Large Vision-Language Models (LVLMs). However, most benchmarks conduct questions by selecting images from existing datasets, resulting in the potential…

Large Language Models (LLMs) have demonstrated exceptional code generation capabilities, yet their token-level mechanisms remain underexplored, particularly in compressed models. Through systematic analysis of programming language token…

To develop a trustworthy AI system, which aim to identify the input regions that most influence the models decisions. The primary task of existing attribution methods lies in efficiently and accurately identifying the relationships among…

Detecting biases in the outputs produced by generative models is essential to reduce the potential risks associated with their application in critical settings. However, the majority of existing methodologies for identifying biases in…

Large language models (LLMs) increasingly mediate decisions in domains where unfair treatment of demographic groups is unacceptable. Existing work probes when biased outputs appear, but gives little insight into the mechanisms that generate…

The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing interpretability methods, particularly those based on activations, often require or assume…

While Large Language Models (LLMs) achieve near-human performance on standard benchmarks, their capabilities often fail to generalize to complex, real-world problems. To bridge this gap, we introduce DeepQuestion, a scalable, automated…

Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based reasoning. However, debugging these models remains a persistent challenge due to their…

The recent developments in deep learning led to the integration of natural language processing (NLP) with computer vision, resulting in powerful integrated Vision and Language Models (VLMs). Despite their remarkable capabilities, these…

Automating software vulnerability detection (SVD) remains a critical challenge in an era of increasingly complex and interdependent software systems. Despite significant advances in Large Language Models (LLMs) for code analysis, prevailing…

Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising performance, LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on…

The popularity of large language models (LLMs) continues to grow, and LLM-based assistants have become ubiquitous. Information security awareness (ISA) is an important yet underexplored area of LLM safety. ISA encompasses LLMs' security…

Tabular machine learning problems often require time-consuming and labor-intensive feature engineering. Recent efforts have focused on using large language models (LLMs) to capitalize on their potential domain knowledge. At the same time,…

Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision systems are increasingly deployed as proprietary black-box APIs, exposing only…

Large Language Models (LLMs) used in creative workflows can reinforce stereotypes and perpetuate inequities, making fairness auditing essential. Existing methods rely on constrained tasks and fixed benchmarks, leaving open-ended creative…

Large Language Models (LLMs) have showcased their remarkable capabilities in diverse domains, encompassing natural language understanding, translation, and even code generation. The potential for LLMs to generate harmful content is a…

Sentiment Analysis (SA) models harbor inherent social biases that can be harmful in real-world applications. These biases are identified by examining the output of SA models for sentences that only vary in the identity groups of the…