Visual description grounding reduces hallucinations and boosts reasoning in lvlms

S Ghosh, CKR Evuru, S Kumar, U Tyagi… - The Thirteenth …, 2024‏ - openreview.net
Large Vision-Language Models (LVLMs) often produce responses that misalign with factual
information, a phenomenon known as hallucinations. While hallucinations are well-studied …

Monotonic paraphrasing improves generalization of language model prompting

Q Liu, F Wang, N Xu, T Yan, T Meng… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Performance of large language models (LLMs) may vary with different prompts or
instructions of even the same task. One commonly recognized factor for this phenomenon is …

Improving open-ended text generation via adaptive decoding

W Zhu, H Hao, Z He, Y Ai, R Wang - arxiv preprint arxiv:2402.18223, 2024‏ - arxiv.org
Current language models decode text token by token according to probabilistic distribution,
and determining the appropriate candidates for the next token is crucial to ensure …

[PDF][PDF] Future Token Prediction--Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Prediction

N Walker - arxiv preprint arxiv:2410.18160, 2024‏ - test.ai-plans.com
Causal decoder-only transformer models used for generative language modelling, such as
Generative Pre-trained Transformers (GPT), are trained to predict the next token in a …

" We Need Structured Output": Towards User-centered Constraints on Large Language Model Output

MX Liu, F Liu, AJ Fiannaca, T Koo, L Dixon… - Extended Abstracts of …, 2024‏ - dl.acm.org
Large language models can produce creative and diverse responses. However, to integrate
them into current developer workflows, it is essential to constrain their outputs to follow …

VDGD: Mitigating LVLM Hallucinations in Cognitive Prompts by Bridging the Visual Perception Gap

S Ghosh, CKR Evuru, S Kumar, U Tyagi… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Recent interest in Large Vision-Language Models (LVLMs) for practical applications is
moderated by the significant challenge of hallucination or the inconsistency between the …