相关论文: Universal Boosts, Specific Suppressors: Sparse Aut…

Chest X-ray report generation (CXR-RG) has the potential to substantially alleviate radiologists' workload. However, conventional autoregressive vision--language models (VLMs) suffer from high inference latency due to sequential token…

Image and language modeling is of crucial importance for vision-language pre-training (VLP), which aims to learn multi-modal representations from large-scale paired image-text data. However, we observe that most existing VLP methods focus…

Despite the significant advancements in Large Vision-Language Models (LVLMs), their tendency to generate hallucinations undermines reliability and restricts broader practical deployment. Among the hallucination mitigation methods, feature…

Sparse autoencoders (SAEs) are widely used for interpreting language model activations. A key evaluation metric is the increase in cross-entropy loss between the original model logits and the reconstructed model logits when replacing model…

As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important. Existing behavioral control methods face significant limitations:…

The mechanisms behind multilingual capabilities in Large Language Models (LLMs) have been examined using neuron-based or internal-activation-based methods. However, these methods often face challenges such as superposition and layer-wise…

Accurate imputation of missing laboratory values in electronic health records (EHRs) is critical to enable robust clinical predictions and reduce biases in AI systems in healthcare. Existing methods, such as XGBoost, softimpute, GAIN,…

The rapid advancements in transformer-based language models have revolutionized natural language processing, yet understanding the internal mechanisms of these models remains a significant challenge. This paper explores the application of…

Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidden activations into more fine-grained, interpretable…

Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing…

Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input. We investigate the root causes…

Sparse autoencoders (SAEs) have emerged as powerful techniques for interpretability of large language models (LLMs), aiming to decompose hidden states into meaningful semantic features. While several SAE variants have been proposed, there…

In medical image classification, supervised learning is challenging due to the scarcity of labeled medical images. To address this, we leverage the visual-textual alignment within Vision-Language Models (VLMs) to enable unsupervised…

Sparse autoencoders (SAEs) are widely used in mechanistic interpretability to project LLM activations onto sparse latent spaces. However, sparsity alone is an imperfect proxy for interpretability, and current training objectives often…

Large vision-language models (LVLMs) often hallucinate objects that are not present in the input image, largely because visual grounding weakens as decoding progresses. Existing inference-time mitigation methods modify logits or hidden…

Vision-Language Models (VLMs) integrate information from multiple modalities and have shown remarkable success across various tasks. However, deploying large-scale VLMs in resource-constrained scenarios is challenging. Pruning followed by…

Medical Vision Language Models (VLMs) can change their answers when clinicians rephrase the same question, a failure mode that threatens deployment safety. We introduce PSF-Med, a benchmark of 26,850 chest X-ray questions paired with 92,856…

Large language models (LLMs) have achieved great success in medical question answering and clinical decision-making, promoting the efficiency and popularization of the personalized virtual doctor in society. However, the traditional…

Variational Autoencoders (VAEs) are powerful generative models for learning latent representations. Standard VAEs generate dispersed and unstructured latent spaces by utilizing all dimensions, which limits their interpretability, especially…

Large vision-language models (LVLMs) suffer from hallucination a lot, generating responses that apparently contradict to the image content occasionally. The key problem lies in its weak ability to comprehend detailed content in a…