LiteCoST / README.md
nielsr's picture
nielsr HF Staff
Add model card and metadata
943d265 verified
|
raw
history blame
1.92 kB
metadata
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation

LiteCoST: Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs

LiteCoST is a two-pillar framework designed to achieve both high accuracy and low latency for long-document question answering (QA) using Small Language Models (SLMs).

The model utilizes Chain-of-Structured-Thought (CoST), a schema-aware instruction template that guides models to produce both a step-wise reasoning trace and a structured output. This approach is distilled into compact models (3B/7B) through a two-stage fine-tuning process: Supervised Fine-Tuning (SFT) for structural alignment, followed by Group Relative Policy Optimization (GRPO) to enhance answer quality and process consistency.

Resources

Method Overview

  1. Pillar 1: Chain-of-Structured-Thought (CoST): Guides a high-capability LLM to generate auditable traces that include structure analysis, trace generation, data verification, and refinement.
  2. Pillar 2: SLM Fine-Tuning: Compact models are trained on the CoST data using SFT and then optimized via GRPO with rewards for answer quality, formatting, and process consistency.

Performance

By distilling structure-first behavior into SLMs, this approach achieves LLM-comparable quality on multi-domain long-document QA while delivering significantly lower latency than GPT-4o and DeepSeek-R1 (671B).

Citation

@inproceedings{cost2026litecost,
  title={Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs},
  author={Liang, Seton and others},
  booktitle={The Fourteenth International Conference on Learning Representations (ICLR)},
  year={2026}
}