SR-LLM: Rethinking the Structured Representation in Large Language Model
This work addresses the challenge of enhancing LLMs' inference capability with structured data, which could improve reasoning and interoperability in natural language processing, though it appears incremental as it builds on existing integration attempts.
The paper tackles the problem of integrating structured representations like AMR into Large Language Models (LLMs), which previously led to inferior performance, and proposes SR-LLM, a framework that improves performance by using natural language descriptions or fine-tuning, achieving gains of up to 12.38% on the PAWS dataset.
Structured representations, exemplified by Abstract Meaning Representation (AMR), have long been pivotal in computational linguistics. However, their role remains ambiguous in the Large Language Models (LLMs) era. Initial attempts to integrate structured representation into LLMs via a zero-shot setting yielded inferior performance. We hypothesize that such a decline stems from the structure information being passed into LLMs in a code format unfamiliar to LLMs' training corpora. Consequently, we propose SR-LLM, an innovative framework with two settings to explore a superior way of integrating structured representation with LLMs from training-free and training-dependent perspectives. The former integrates structural information through natural language descriptions in LLM prompts, whereas its counterpart augments the model's inference capability through fine-tuning on linguistically described structured representations. Performance improvements were observed in widely downstream datasets, with particularly notable gains of 3.17% and 12.38% in PAWS. To the best of our knowledge, this work represents the pioneering demonstration that leveraging structural representations can substantially enhance LLMs' inference capability. We hope that our work sheds light and encourages future research to enhance the reasoning and interoperability of LLMs by structure data.