Related papers: Truth-Aware Decoding: A Program-Logic Approach to …

Multimodal Large Language Models (MLLMs) often suffer from hallucinations, particularly errors in object existence, attributes, or relations, which undermine their reliability. We introduce TACO (Verified Atomic Confidence Estimation), a…

Speculative decoding (SD) accelerates large language model (LLM) reasoning by using a small draft model to generate candidate tokens, which the target LLM either accepts directly or regenerates upon rejection. However, excessive alignment…

Despite their ability to aid developers in detecting potential defects early in the software development life cycle, static analysis tools often suffer from precision issues (i.e., high false positive rates of reported alarms). To improve…

With recent advances in speech synthesis including text-to-speech (TTS) and voice conversion (VC) systems enabling the generation of ultra-realistic audio deepfakes, there is growing concern about their potential misuse. However, most…

Despite their impressive capabilities, large language models (LLMs) are prone to hallucinations, i.e., generating content that deviates from facts seen during pretraining. We propose a simple decoding strategy for reducing hallucinations…

We introduce a new distributed policy gradient algorithm and show that it outperforms existing reward-aware training procedures such as REINFORCE, minimum risk training (MRT) and proximal policy optimization (PPO) in terms of training…

In this paper, we address the hallucination problem commonly found in natural language generation tasks. Language models often generate fluent and convincing content but can lack consistency with the provided source, resulting in potential…

Language models have demonstrated remarkable capabilities in reasoning tasks through test-time scaling techniques like best-of-N sampling and tree search. However, these approaches often demand substantial computational resources, creating…

Retrieval-Augmented Generation (RAG) has been proposed to mitigate hallucinations in large language models (LLMs), where generated outputs may be factually incorrect. However, existing RAG approaches predominantly rely on vector similarity…

Guaranteeing the correctness and factuality of language model (LM) outputs is a major open problem. In this work, we propose conformal factuality, a framework that can ensure high probability correctness guarantees for LMs by connecting…

Large language models (LLMs) have demonstrated exceptional proficiency in language understanding. However, when LLMs align their outputs with deceptive and/or misleading prompts, the generated responses could deviate from the de facto…

Speculative decoding has emerged as a promising approach to accelerate inference in vision-language models (VLMs) by enabling parallel verification of multiple draft tokens. However, existing methods rely on static tree structures that…

Learning-based systems are increasingly deployed across various domains, yet the complexity of traditional neural networks poses significant challenges for formal verification. Unlike conventional neural networks, learned Logic Gate…

Retrieval-Augmented Generation (RAG) improves reliability of large language models by incorporating external knowledge, but the retrieval process can introduce bias that propagates to generated outputs. This issue is particularly…

Most efforts to improve the reasoning capabilities of large language models (LLMs) involve either scaling the number of parameters and the size of training data, or scaling inference computation by letting models generate complex chains of…

Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning. Recent multi-modal OOD detection leverages textual information from in-distribution (ID) class names for visual OOD detection, yet it currently…

We introduce Text-based Explainable Video Anomaly Detection (TbVAD), a language-driven framework for weakly supervised video anomaly detection that performs anomaly detection and explanation entirely within the textual domain. Unlike…

Speculative decoding accelerates inference in large language models (LLMs) by generating draft tokens for target model verification. Current approaches for obtaining draft tokens rely on lightweight draft models or additional model…

While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination and untruthful responses, particularly when tasks demand information outside their parametric…

The increasing prevalence of audio deepfakes poses significant security threats, necessitating robust detection methods. While existing detection systems exhibit promise, their robustness against malicious audio manipulations remains…