Towards Better Understanding Table Instruction Tuning: Decoupling the Effects from Data versus Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917902201913344 |
|---|---|
| author | Deng, Naihao Zhang, Sheng Zhu, Henghui Chang, Shuaichen Zhang, Jiani Li, Alexander Hanbo Hang, Chung-Wei Kobayashi, Hideo Hu, Yiqun Ng, Patrick |
| author_facet | Deng, Naihao Zhang, Sheng Zhu, Henghui Chang, Shuaichen Zhang, Jiani Li, Alexander Hanbo Hang, Chung-Wei Kobayashi, Hideo Hu, Yiqun Ng, Patrick |
| contents | Recent advances in natural language processing have leveraged instruction tuning to enhance Large Language Models (LLMs) for table-related tasks. However, previous works train different base models with different training data, lacking an apples-to-apples comparison across the result table LLMs. To address this, we fine-tune base models from the Mistral, OLMo, and Phi families on existing public training datasets. Our replication achieves performance on par with or surpassing existing table LLMs, establishing new state-of-the-art performance on Hitab, a table question-answering dataset. More importantly, through systematic out-of-domain evaluation, we decouple the contributions of training data and the base model, providing insight into their individual impacts. In addition, we assess the effects of table-specific instruction tuning on general-purpose benchmarks, revealing trade-offs between specialization and generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_14717 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Better Understanding Table Instruction Tuning: Decoupling the Effects from Data versus Models Deng, Naihao Zhang, Sheng Zhu, Henghui Chang, Shuaichen Zhang, Jiani Li, Alexander Hanbo Hang, Chung-Wei Kobayashi, Hideo Hu, Yiqun Ng, Patrick Computation and Language Recent advances in natural language processing have leveraged instruction tuning to enhance Large Language Models (LLMs) for table-related tasks. However, previous works train different base models with different training data, lacking an apples-to-apples comparison across the result table LLMs. To address this, we fine-tune base models from the Mistral, OLMo, and Phi families on existing public training datasets. Our replication achieves performance on par with or surpassing existing table LLMs, establishing new state-of-the-art performance on Hitab, a table question-answering dataset. More importantly, through systematic out-of-domain evaluation, we decouple the contributions of training data and the base model, providing insight into their individual impacts. In addition, we assess the effects of table-specific instruction tuning on general-purpose benchmarks, revealing trade-offs between specialization and generalization. |
| title | Towards Better Understanding Table Instruction Tuning: Decoupling the Effects from Data versus Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2501.14717 |