Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability
This addresses the issue of unreliable and hard-to-update language models for users in AI and NLP, offering a novel training approach that is incremental in leveraging existing reasoning capabilities.
The paper tackles the problem of language models lacking globally coherent and updatable world knowledge, which leads to incorrect content generation and difficulty in editing. It introduces Deductive Closure Training (DCT), a self-supervised method that uses LMs to generate and verify implications from seed documents, resulting in improvements of 3-26% in fact verification and text generation accuracy across datasets.
While language models (LMs) can sometimes generate factually correct text and estimate truth values of individual claims, these generally do not reflect a globally coherent, manipulable model of the world. As a consequence, current LMs also generate incorrect or nonsensical content, and are difficult to edit and bring up to date. We present a method called Deductive Closure Training (DCT) that uses LMs themselves to identify implications of (and contradictions within) the text that they generate, yielding an efficient self-supervised procedure for improving LM factuality. Given a collection of seed documents, DCT prompts LMs to generate additional text implied by these documents, reason globally about the correctness of this generated text, and finally fine-tune on text inferred to be correct. Given seed documents from a trusted source, DCT provides a tool for supervised model updating; if seed documents are sampled from the LM itself, DCT enables fully unsupervised fine-tuning for improved coherence and accuracy. Across the CREAK, MQUaKE, and Reversal Curse datasets, supervised DCT improves LM fact verification and text generation accuracy by 3-26%; on CREAK fully unsupervised DCT improves verification accuracy by 12%. These results show that LMs' reasoning capabilities during inference can be leveraged during training to improve their reliability.