Paper
LLMs & Texto
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
Large language models exhibit data referencing errors when processing tables, which can be mitigated through critic-based filtering and rejection sampling, with a lightweight 4B-pa…
Hugging Face · Daily Papers
·Yuqing Yang, Qi Zhu
·
·▲ 3 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Yuqing Yang, Qi Zhu, Zhen Han, Boran Han, Zhengyuan Shen, Shuai Wang
- 3 upvotes da comunidade
- Temas: large language models, data referencing errors, table tasks, answer accuracy, critic-based filtering, rejection sampling
Resumo
Resumo original (em inglês), extraído do paper:
Large language models exhibit data referencing errors when processing tables, which can be mitigated through critic-based filtering and rejection sampling, with a lightweight 4B-parameter model achieving high detection accuracy.Onde ler
// relacionados
Leia também
Editorial
Claude Sonnet 5: a Anthropic aposta que o modelo do meio faz o trabalho do topo
Blog
Google’s AI buildout drove 37% increase in electricity use in 2025
Blog
OpenAI reportedly offers the Trump administration a five percent stake in the company
Blog