Related papers: CAGE: A Framework for Culturally Adaptive Red-Team…

We propose a novel method that leverages sparse autoencoders (SAEs) and clustering techniques to analyze the internal token representations of large language models (LLMs) and guide generations in mathematical reasoning tasks. Our approach…

Assessing progress toward the Sustainable Development Goals (SDGs) requires multi-step reasoning over visual cues, contextual knowledge, and development indicators, where incomplete evidence use and imperfect evidence integration can…

Online memes are a powerful yet challenging medium for content moderation, often masking harmful intent behind humor, irony, or cultural symbolism. Conventional moderation systems "especially those relying on explicit text" frequently fail…

Multimodal classifiers function as opaque black box models. While several techniques exist to interpret their predictions, very few of them are as intuitive and accessible as natural language explanations (NLEs). To build trust, such…

As large language models grow in capability and agency, identifying vulnerabilities through red-teaming becomes vital for safe deployment. However, traditional prompt-engineering approaches may prove ineffective once red-teaming turns into…

End-to-end conversational recommendation systems (CRS) generate responses by leveraging both dialog history and a knowledge base (KB). A CRS mainly faces three key challenges: (1) at each turn, it must decide if recommending a KB entity is…

Ensuring the safety and reliability of large language models (LLMs) in clinical practice is critical to prevent patient harm. However, LLMs are advancing so rapidly that static benchmarks quickly become obsolete or prone to overfitting,…

Despite recent advances, Large Language Models (LLMs) still generate vulnerable code. Retrieval-Augmented Generation (RAG) has the potential to enhance LLMs for secure code generation by incorporating external security knowledge. However,…

Conditional Tabular Generative Adversarial Networks (CTGAN) and their various derivatives are attractive for their ability to efficiently and flexibly create synthetic tabular data, showcasing strong performance and adaptability. However,…

Image captioning is a challenging computer vision task, which aims to generate a natural language description of an image. Most recent researches follow the encoder-decoder framework which depends heavily on the previous generated words for…

AI-based code generation is increasingly prevalent, with GitHub Copilot estimated to generate 46% of the code on GitHub. Accurately evaluating how well generated code aligns with developer intent remains a critical challenge. Traditional…

Vision-Language-Action (VLA) models have achieved remarkable success in robotic manipulation. However, their robustness to linguistic nuances remains a critical, under-explored safety concern, posing a significant safety risk to real-world…

This paper proposes Meta-SAGE, a novel approach for improving the scalability of deep reinforcement learning models for combinatorial optimization (CO) tasks. Our method adapts pre-trained models to larger-scale problems in test time by…

Recent vision-language models (VLMs) face significant challenges in test-time adaptation to novel domains. While cache-based methods show promise by leveraging historical information, they struggle with both caching unreliable feature-label…

Ensuring the safety of large language models (LLMs) is paramount, yet identifying potential vulnerabilities is challenging. While manual red teaming is effective, it is time-consuming, costly and lacks scalability. Automated red teaming…

LLM-based agents are increasingly deployed for expert decision support, yet human-AI teams in high-stakes settings do not yet reliably outperform the best individual. We argue this complementarity gap reflects a fundamental mismatch:…

Text-image cross-modal retrieval is a challenging task in the field of language and vision. Most previous approaches independently embed images and sentences into a joint embedding space and compare their similarities. However, previous…

We present a comprehensive framework for enhancing Retrieval-Augmented Generation (RAG) systems through dynamic retrieval strategies and reinforcement fine-tuning. This approach significantly improves large language models on…

Many safety post-training methods for large language models (LLMs) are designed to modify the model's behaviour from producing unsafe answers to issuing refusals. However, such distribution shifts are often brittle and degrade performance…

Meme-based social abuse detection is challenging because harmful intent often relies on implicit cultural symbolism and subtle cross-modal incongruence. Prior approaches, from fusion-based methods to in-context learning with Large…