Related papers: Chain-based Adaptive Reconfiguration Over Lattices…
This paper explores hallucination phenomena in large language models (LLMs) through the lens of language philosophy and psychoanalysis. By incorporating Lacan's concepts of the "chain of signifiers" and "suture points," we propose the…
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…
Speculative decoding is a powerful technique that accelerates Large Language Model (LLM) inference by leveraging a lightweight speculative draft model. However, existing designs suffers in performance due to misalignment between training…
Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. However, existing approaches typically implement iterative refinement at the application or prompting…
Large language models (LLMs) can generate fluent natural language texts when given relevant documents as background context. This ability has attracted considerable interest in developing industry applications of LLMs. However, LLMs are…
As reasoning modules, such as the chain-of-thought mechanism, are applied to large language models, they achieve strong performance on various tasks such as answering common-sense questions and solving math problems. The main challenge now…
Using Reinforcement Learning (RL) to learn new robotic tasks from scratch is often inefficient. Leveraging prior knowledge has the potential to significantly enhance learning efficiency, which, however, raises two critical challenges: how…
Hallucinations in vision-language models pose a significant challenge to their reliability, particularly in the generation of long captions. Current methods fall short of accurately identifying and mitigating these hallucinations. To…
Diffusion language models (DLMs) expose their denoising trajectories, offering a natural handle for inference-time control; accordingly, an ideal hallucination mitigation framework should intervene during generation using this model-native…
Large language models generate outputs stochastically and may produce fluent but invalid responses, including factual hallucinations. Existing mitigation strategies reduce average error rates but do not provide explicit control over the…
Hallucination, where large language models (LLMs) generate confident but incorrect or irrelevant information, remains a key limitation in their application to complex, open-ended tasks. Chain-of-thought (CoT) prompting has emerged as a…
Large language models (LLMs) often generate fluent but factually incorrect statements despite having access to relevant evidence, a failure mode rooted in how they allocate attention between contextual and parametric knowledge.…
Reducing hallucinations in Large Language Models (LLMs) is essential for improving the accuracy of data extraction from large text corpora. Current methods, like prompt engineering and chain-of-thought prompting, focus on individual…
Linguistic cues such as "I believe" and "probably" offer an intuitive interface for communicating confidence, yet a generalisable, principled calibration framework for linguistic confidence expressions remains underexplored. In particular,…
We present a reinforcement learning (RL) framework in which the learned policy comes with a machine-checkable certificate of provable adversarial robustness. Our approach, called CAROL, learns a model of the environment. In each learning…
Large language models (LLMs) exhibit persistent miscalibration, especially after instruction tuning and preference alignment. Modified training objectives can improve calibration, but retraining is expensive. Inference-time steering offers…
This work introduces a novel methodology for the automatic detection of hallucinations generated during large language model (LLM) inference. The proposed approach is based on a systematic taxonomy and controlled reproduction of diverse…
Large language models (LLMs) have experienced notable advancements in generating coherent and contextually relevant responses. However, hallucinations - incorrect or unfounded claims - are still prevalent, prompting the creation of…
Large Vision-Language Models have shown strong multimodal reasoning capabilities, yet they remain susceptible to object hallucinations when language priors dominate insufficient or misaligned visual evidence. Training-free contrastive…
Large language models (LLMs) have revolutionized the field of natural language processing with their impressive reasoning and question-answering capabilities. However, these models are sometimes prone to generating credible-sounding but…