Related papers: Hallucination reduction with CASAL: Contrastive Ac…
When asked to summarize articles or answer questions given a passage, large language models (LLMs) can hallucinate details and respond with unsubstantiated answers that are inaccurate with respect to the input context. This paper describes…
Learning self-supervised representations using reconstruction or contrastive losses improves performance and sample complexity of image-based and multimodal reinforcement learning (RL). Here, different self-supervised loss functions have…
As large language models (LLMs) evolve in complexity and capability, the efficacy of less widely deployed alignment techniques are uncertain. Building on previous work on activation steering and contrastive activation addition (CAA), this…
Large Vision-Language Models (VLMs) often exhibit text inertia, where attention drifts from visual evidence toward linguistic priors, resulting in object hallucinations. Existing decoding strategies intervene only at the output logits and…
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, yet they remain susceptible to hallucinations -- generating content that is factually incorrect, unfaithful to provided…
Recent advancements in audio-aware large language models (ALLMs) enable them to process and understand audio inputs. However, these models often hallucinate non-existent sound events, reducing their reliability in real-world applications.…
Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…
Nowadays, the research on Large Vision-Language Models (LVLMs) has been significantly promoted thanks to the success of Large Language Models (LLM). Nevertheless, these Vision-Language Models (VLMs) are suffering from the drawback of…
Large Language Models (LLMs) have demonstrated remarkable fluency across a range of natural language tasks, yet remain vulnerable to hallucinations - factual inaccuracies that undermine trust in real world deployment. We present…
Multimodal large language models achieve strong performance across diverse tasks but remain prone to hallucinations, where outputs are not grounded in visual inputs. This issue can be attributed to two main biases: text-visual bias, the…
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in multimodal task reasoning. However, they often generate responses that appear plausible yet do not accurately reflect the visual content, a phenomenon known…
Hallucinations in Large Language Models (LLMs) pose a major barrier to their reliable use in critical decision-making. Although existing hallucination detection methods have improved accuracy, they still struggle with disentangling semantic…
Large language models (LLMs) demonstrate exceptional capabilities, yet still face the hallucination issue. Typical text generation approaches adopt an auto-regressive generation without deliberate reasoning, which often results in…
Large language models (LLMs) are promising tools for supporting security management tasks, such as incident response planning. However, their unreliability and tendency to hallucinate remain significant challenges. In this paper, we address…
Large Language Models (LLMs) achieve remarkable performance through pretraining on extensive data. This enables efficient adaptation to diverse downstream tasks. However, the lack of interpretability in their underlying mechanisms limits…
Hallucination is a major concern in LLM-driven service systems, necessitating explicit knowledge grounding for compliance-guaranteed responses. In this paper, we introduce Retrieval-Augmented Learning-to-Match (RAL2M), a novel framework…
Large Language Models (LLMs), despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim to mitigate this by manipulating model internals, but have a potential risk of…
To mitigate hallucinations in large language models (LLMs), we propose a framework that focuses on errors induced by prompts. Our method extends a chain-style knowledge distillation approach by incorporating a programmable module that…
We introduce Contrastive Activation Addition (CAA), an innovative method for steering language models by modifying their activations during forward passes. CAA computes "steering vectors" by averaging the difference in residual stream…
Large Language Models (LLMs) have significantly advanced communications fields, such as Telecom Q\&A, mathematical modeling, and coding. However, LLMs encounter an inherent issue known as hallucination, i.e., generating fact-conflicting or…