Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.08971 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912780784762880 |
|---|---|
| author | Lee, Minho Min, Junghyun Kim, Yerang Lee, Woochul Lee, Yeonsoo |
| author_facet | Lee, Minho Min, Junghyun Kim, Yerang Lee, Woochul Lee, Yeonsoo |
| contents | Modern generative pre-trained language models excel at open-ended text generation, yet continue to underperform on structure-related tasks such as NER, relation extraction, and semantic role labeling, especially when compared to encoder-only models of similar sizes. While this gap has been attributed to limited structure knowledge, we hypothesize this is also due to the missing connection between the model's internal representations of linguistic structure and the output space used during supervised fine-tuning. We propose the Structured Language Generation Model (SLGM), a model- and task-agnostic framework that reformulates structured prediction as a classification problem through three components: (1) reinforced input formatting with structural cues, (2) loss design, and (3) format-aware decoding that constrains generation to task-valid outputs. Across 5 tasks and 13 datasets, SLGM substantially improves structure prediction without relying on dataset-specific engineering or additional model parameters, strengthening alignment between the model's internal structure representation and output. It outperforms baseline fine-tuning on models of the same size, achieves comparable performance to much larger models when used with <1B parameter models, and acts as a zero-weight adapter that reproduces the benefits of dataset-specific fine-tuning in low-resource settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_08971 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Structured Language Generation Model: Loss Calibration and Formatted Decoding for Robust Structure Prediction and Knowledge Retrieval Lee, Minho Min, Junghyun Kim, Yerang Lee, Woochul Lee, Yeonsoo Computation and Language Modern generative pre-trained language models excel at open-ended text generation, yet continue to underperform on structure-related tasks such as NER, relation extraction, and semantic role labeling, especially when compared to encoder-only models of similar sizes. While this gap has been attributed to limited structure knowledge, we hypothesize this is also due to the missing connection between the model's internal representations of linguistic structure and the output space used during supervised fine-tuning. We propose the Structured Language Generation Model (SLGM), a model- and task-agnostic framework that reformulates structured prediction as a classification problem through three components: (1) reinforced input formatting with structural cues, (2) loss design, and (3) format-aware decoding that constrains generation to task-valid outputs. Across 5 tasks and 13 datasets, SLGM substantially improves structure prediction without relying on dataset-specific engineering or additional model parameters, strengthening alignment between the model's internal structure representation and output. It outperforms baseline fine-tuning on models of the same size, achieves comparable performance to much larger models when used with <1B parameter models, and acts as a zero-weight adapter that reproduces the benefits of dataset-specific fine-tuning in low-resource settings. |
| title | Structured Language Generation Model: Loss Calibration and Formatted Decoding for Robust Structure Prediction and Knowledge Retrieval |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.08971 |