Fact Grounded Attention: Eliminating Hallucination in Large Language Models Through Attention Level Knowledge Integration
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908572730785792 |
|---|---|
| author | Gupta, Aayush |
| author_facet | Gupta, Aayush |
| contents | "The greatest enemy of knowledge is not ignorance, it is the illusion of knowledge." Large Language Models have conquered natural language but remain prisoners of their own probabilistic nature--confidently hallucinating facts they never truly knew. We present Fact Grounded Attention (FGA), a novel architectural modification that transforms unreliable language models into deterministic truth tellers by injecting verifiable knowledge directly into the attention mechanism. Unlike existing approaches that patch hallucinations after generation or prepend retrieved text, FGA intervenes at the mathematical heart of the transformer--the pre-softmax attention scores--creating a model that cannot hallucinate when facts exist in its knowledge base. Our experiments across 1,107 technical queries spanning smartphones, laptops, and electric vehicles demonstrate a transformation from 6.3% accuracy in vanilla Llama 3.2 to 99.7% accuracy with FGA. More critically, knowledge updates occur in under one second without retraining, compared to hours for parameter editing approaches. FGA doesn't just reduce hallucination--it eliminates it entirely for verifiable facts, marking a fundamental shift from probabilistic approximation to deterministic precision in neural language generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25252 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fact Grounded Attention: Eliminating Hallucination in Large Language Models Through Attention Level Knowledge Integration Gupta, Aayush Artificial Intelligence 68T50, 68T05, 68T30 I.2.7; I.2.6; H.3.3 "The greatest enemy of knowledge is not ignorance, it is the illusion of knowledge." Large Language Models have conquered natural language but remain prisoners of their own probabilistic nature--confidently hallucinating facts they never truly knew. We present Fact Grounded Attention (FGA), a novel architectural modification that transforms unreliable language models into deterministic truth tellers by injecting verifiable knowledge directly into the attention mechanism. Unlike existing approaches that patch hallucinations after generation or prepend retrieved text, FGA intervenes at the mathematical heart of the transformer--the pre-softmax attention scores--creating a model that cannot hallucinate when facts exist in its knowledge base. Our experiments across 1,107 technical queries spanning smartphones, laptops, and electric vehicles demonstrate a transformation from 6.3% accuracy in vanilla Llama 3.2 to 99.7% accuracy with FGA. More critically, knowledge updates occur in under one second without retraining, compared to hours for parameter editing approaches. FGA doesn't just reduce hallucination--it eliminates it entirely for verifiable facts, marking a fundamental shift from probabilistic approximation to deterministic precision in neural language generation. |
| title | Fact Grounded Attention: Eliminating Hallucination in Large Language Models Through Attention Level Knowledge Integration |
| topic | Artificial Intelligence 68T50, 68T05, 68T30 I.2.7; I.2.6; H.3.3 |
| url | https://arxiv.org/abs/2509.25252 |