Related papers: Concept Tokens: Learning Behavioral Embeddings Thr…

We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined only through their interactions in-context. While prior work has studied…

Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certainty, which hinders their usage in high-stakes domains. Existing verbalized confidence…

Adversarial attacks aim to generate malicious inputs that mislead deep models, but beyond causing model failure, they cannot provide certain interpretable information such as ``\textit{What content in inputs make models more likely to…

Large language models (LLMs) demonstrate great performance in text generation. However, LLMs are still suffering from hallucinations. In this work, we propose an inference-time method, Self-Highlighted Hesitation (SH2), to help LLMs decode…

As large language models (LLMs) become widely deployed, concerns about their safety and alignment grow. An approach to steer LLM behavior, such as mitigating biases or defending against jailbreaks, is to identify which parts of a prompt…

Large language models (LLMs) have demonstrated impressive performance on several tasks and are increasingly deployed in real-world applications. However, especially in high-stakes settings, it becomes vital to know when the output of an LLM…

While Large Vision-Language Models (LVLMs) have rapidly advanced in recent years, the prevalent issue known as the `hallucination' problem has emerged as a significant bottleneck, hindering their real-world deployments. Existing methods…

Recent studies have examined attention dynamics in large vision-language models (LVLMs) to detect hallucinations. However, existing approaches remain limited in reliably distinguishing hallucinated from factually grounded outputs, as they…

Vision-Language Models (VLMs) often suffer from hallucination, partly due to challenges in aligning multimodal information. We propose Prompt-in-Image, a simple method that embeds textual instructions directly into images. This removes the…

Current language models rely on static vocabularies determined at pretraining time, which can lead to decreased performance and increased computational cost for domains underrepresented in the original vocabulary. New tokens can be added to…

Multimodal Large Language Models (MLLMs) frequently suffer from hallucination issues, generating information about objects that are not present in input images during vision-language tasks. These hallucinations particularly undermine model…

Large Multimodal Models (LMMs) often suffer from multimodal hallucinations, wherein they may create content that is not present in the visual inputs. In this paper, we explore a new angle of this issue: overly detailed training data hinders…

Concept Bottleneck Models (CBMs) offer inherent interpretability by initially translating images into human-comprehensible concepts, followed by a linear combination of these concepts for classification. However, the annotation of concepts…

Large Vision-Language Models (LVLMs) have shown remarkable performance on many visual-language tasks. However, these models still suffer from multimodal hallucination, which means the generation of objects or content that violates the…

Reinforcement-learning-based post-training has become a key approach for improving the reasoning ability of large language models, but its token-level learning signals remain poorly understood. This work studies their heterogeneity through…

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Large language models (LLMs) often generate responses that deviate from user input or training data, a phenomenon known as "hallucination." These hallucinations undermine user trust and hinder the adoption of generative AI systems.…

Hallucinations pose a significant challenge to the reliability and alignment of Large Language Models (LLMs), limiting their widespread acceptance beyond chatbot applications. Despite ongoing efforts, hallucinations remain a prevalent…

Token embeddings play a crucial role in language modeling but, despite this practical relevance, their theoretical understanding remains limited. Our paper addresses the gap by characterizing the structure of embeddings obtained via…

Large language models (LLMs) often exhibit undesirable behaviors, such as hallucinations and sequence repetitions. We propose to view these behaviors as fallbacks that models exhibit under epistemic uncertainty, and investigate the…