# Open-domain Implicit Format Control for Large Language Model Generation

arXiv: https://arxiv.org/abs/2408.04392 · HTML: https://mlsanity.com/paper/2408.04392/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 23 references that are in the map.
- First posted on arXiv 8 Aug 2024.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [Controlled Text Generation with Natural Language Instructions](https://mlsanity.com/paper/2304.14293/) (2023)
- [AlignBench: Benchmarking Chinese Alignment of Large Language Models](https://mlsanity.com/paper/2311.18743/) (2023)
- [DeAL: Decoding-time Alignment for Large Language Models](https://mlsanity.com/paper/2402.06147/) (2024)
- [Aligning Language Models with Demonstrated Feedback](https://mlsanity.com/paper/2406.00888/) (2024)
- [Faithfulness-Aware Decoding Strategies for Abstractive Summarization](https://mlsanity.com/paper/2303.03278/) (2023)
- [Tele-FLM Technical Report](https://mlsanity.com/paper/2404.16645/) (2024)
- [52B to 1T: Lessons Learned via Tele-FLM Series](https://mlsanity.com/paper/2407.02783/) (2024)
- [Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access](https://mlsanity.com/paper/2401.09967/) (2024)

## Built on by (most cited first, 2 of 2)

- [CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning](https://mlsanity.com/paper/2411.16313/) (2024)
- [Sketch: A Toolkit for Streamlining LLM Operations](https://mlsanity.com/paper/2409.03346/) (2024)

## Abstract (arXiv)

Controlling the format of outputs generated by large language models (LLMs) is a critical functionality in various applications. Current methods typically employ constrained decoding with rule-based automata or fine-tuning with manually crafted format instructions, both of which struggle with open-domain format requirements. To address this limitation, we introduce a novel framework for controlled generation in LLMs, leveraging user-provided, one-shot QA pairs. This study investigates LLMs' capabilities to follow open-domain, one-shot constraints and replicate the format of the example answers. We observe that this is a non-trivial problem for current LLMs. We also develop a dataset collection methodology for supervised fine-tuning that enhances the open-domain format control of LLMs without degrading output quality, as well as a benchmark on which we evaluate both the helpfulness and format correctness of LLM outputs. The resulting datasets, named OIFC-SFT, along with the related code, will be made publicly available at https://github.com/cofe-ai/OIFC.