REVIEW 4 cited by
Towards Verifiable Text Generation with Symbolic References
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original 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 experiments, 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. Our code will be available at http://symgen.github.io.
Forward citations
Cited by 4 Pith papers
-
Issue Retrieval and Verification Enhanced Supplementary Code Comment Generation
IsComment generates supplementary code comments by retrieving issue-report sentences with an LLM and filtering them for code relevance and issue verifiability, reporting coverage of manual comments up to 88.4%.
-
ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models
Fine-tuning InternVL2 on generated interleaved image-text conversations substantially improves contextual image referencing in RAG chatbots, with a new benchmark and metrics.
-
LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review
A logic-controlled pipeline with source mapping and sentence-level attribution generates discharge summaries that score higher than a GPT-4o chain-of-thought baseline in this study.
-
Autoformalization in the Era of Large Language Models: A Survey
A literature review of LLM-based autoformalization, covering datasets, workflows, benchmarks, and its potential role in verifying AI outputs.
Discussion (0). Continue with ORCID to comment.