# Clinical Reasoning Under a Partially Observed Objective in Cone Beam CT Report Generation

arXiv: https://arxiv.org/abs/2609.13238 · HTML: https://mlsanity.com/paper/2609.13238/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 6 of 6)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [MAIRA-2: Grounded Radiology Report Generation](https://mlsanity.com/paper/2406.04449/) (2024)
- [Why rankings of biomedical image analysis competitions should be interpreted with care](https://mlsanity.com/paper/1806.02051/) (2018)
- [BIAS: Transparent reporting of biomedical image analysis challenges](https://mlsanity.com/paper/1910.04071/) (2019)

## Abstract (arXiv)

Maxillofacial report generation from cone beam computed tomography is scored here by a composite objective placing 80% of its weight on a large language model judgement of factual entailment and 20% on lexical overlap, of which only the lexical fifth is visible during development. The grader's BLEU-4 and METEOR routines are reproduced in pure Python and match the reference to machine precision, and an offline entailment surrogate, which tells a report written for one patient from one written for another at an area under the curve of 0.987, makes the composite objective cheap enough to optimise directly. Over the 622-case public release, a report selected against the visible lexical ranking scores 0.2909, whereas one selected against the composite objective scores 0.4122, because pursuing n-gram overlap drives entailment precision from 0.522 down to 0.266. A 29 million parameter encoder fine-tuned on the release reaches a prevalence-weighted out-of-fold area under the curve of 0.486 over 985 statements, indistinguishable from the corpus prior, while nine numbers read from the image header reach 0.945 for mandible coverage and 0.872 for condyle coverage, and acquisition centre alone predicts sentence choice at 0.718 against 0.663 for the image-derived model, identifying dictation convention rather than anatomy as the quantity the lexical metrics reward. The delivered system emits eight unconditional statements and five gated on header geometry under polarity, laterality and tooth-level consistency constraints, and reaches METEOR 0.3542 over 50 held-out cases from an unseen centre. The dataset and code are available at https://github.com/GIND123/CBCT-Clinical-Reasoner