New dataset enhances multi-table Q&A with synthetic reasoning traces

Researchers have developed a new method for multi-table question answering by creating a synthetic dataset of reasoning traces. This dataset, generated using large language models, includes both correct and plausible incorrect reasoning paths. Fine-tuning open-weight models like Qwen3-14B, Mistral-8B, and Llama-3.1-8B with this contrastive data significantly improved their question-answering performance compared to standard supervised fine-tuning. AI

IMPACT Introduces a novel dataset and fine-tuning technique to improve LLM performance on complex relational data reasoning tasks.

RANK_REASON The cluster contains an academic paper detailing a new method and dataset for improving multi-table question answering. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Contrastive Preference Optimization
• Llama-3.1-8B
• Mistral-8B
• Qwen3-14B

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →