Towards Verifiable Text Generation with Symbolic References

Lucas Torroba Hennigen, Zejiang Shen, Aniruddha Nrusimha, Bernhard Gapp, David Sontag, Yoon Kim

Research Area: LMs and interactions, LMs with tools and code

Keywords: attribution, verification of llm generations, symbolic linking, placeholder, template generation

TL;DR: SymGen is a method that prompts an LLM to interleave its regular output text with explicit symbolic references to fields in the source data; it enables easier human verification of the generation.

Abstract: LLMs are vulnerable to hallucinations, and thus their outputs generally require laborious human verification for high-stakes applications. To this end, we propose symbolically grounded generation (SymGen) as a simple approach for enabling easier manual validation of an LLM’s output. SymGen prompts an LLM to interleave its regular output text with explicit symbolic references to fields present in some conditioning data (e.g., a table in JSON format). The references can be used to display the provenance of different spans of text in the generation, reducing the effort required for manual verification. Across a range of data-to-text and question-answering exper- iments, we find that LLMs are able to directly output text that makes use of accurate symbolic references while maintaining fluency and factuality. In a human study we further find that such annotations can streamline human verification of machine-generated text.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 444