Mapping the Course for Prompt-based Structured Prediction
This addresses structured prediction issues in LLMs for NLP applications, but it is incremental as it builds on existing methods.
The paper tackles the problem of hallucinations and complex reasoning in LLMs for structured prediction by combining LLMs with combinatorial inference, showing that this addition leads to more consistent and accurate predictions regardless of prompting strategy, and that calibration and fine-tuning further improve performance on challenging tasks.
LLMs have been shown to be useful for a variety of language tasks, without requiring task-specific fine-tuning. However, these models often struggle with hallucinations and complex reasoning problems due to their autoregressive nature. We propose to address some of these issues, specifically in the area of structured prediction, by combining LLMs with combinatorial inference in an attempt to marry the predictive power of LLMs with the structural consistency provided by inference methods. We perform exhaustive experiments in an effort to understand which prompting strategies can effectively estimate LLM confidence values for use with symbolic inference, and show that, regardless of the prompting strategy, the addition of symbolic inference on top of prompting alone leads to more consistent and accurate predictions. Additionally, we show that calibration and fine-tuning using structured prediction objectives leads to increased performance for challenging tasks, showing that structured learning is still valuable in the era of LLMs.