Do LLMs Make More Mistakes If They Do Not Believe the Input Data?
This story is from 2026-09-10. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.09363v1 Announce Type: new Abstract: Large language models (LLMs) are prone to hallucinating or misinterpreting facts, which impairs their usability in retrieval-augmented generation or data-to-text systems. We analyse how faithfulness of LLMs to provided context depends on how plausible…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-09-10 04:00 · arXiv cs.CL
Do LLMs Make More Mistakes If They Do Not Believe the Input Data?