Výsledky vyhledávání

Report

Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback

Autor: Zadeh, Fatemeh Pesaran, Kim, Juyeon, Kim, Jin-Hwa, Kim, Gunhee

Large language models (LLMs) have demonstrated strong capabilities across various language tasks, notably through instruction-tuning methods. However, LLMs face challenges in visualizing complex, real-world data through charts and plots. Firstly, exi

Externí odkaz: http://arxiv.org/abs/2410.04064

Zobrazit plný text záznamu

Report

Small Language Models are Equation Reasoners

Autor: Kim, Bumjun, Lee, Kunha, Kim, Juyeon, Lee, Sangam

Chain-of-Thought (CoT) reasoning has enabled Large Language Model (LLM) to achieve remarkable performance in various NLP tasks, including arithmetic problem-solving. However, this success does not generalize to small language model (sLM) like T5, due

Externí odkaz: http://arxiv.org/abs/2409.12393

Zobrazit plný text záznamu

Report

Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responses

Autor: Kim, Juyeon, Lee, Jeongeun, Chang, Yoonho, Choi, Chanyeol, Kim, Junseong, Sohn, Jy-yong

Mitigating hallucination issues is a key challenge that must be overcome to reliably deploy large language models (LLMs) in real-world scenarios. Recently, various methods have been proposed to detect and revise factual errors in LLM-generated texts,

Externí odkaz: http://arxiv.org/abs/2402.17097

Zobrazit plný text záznamu