aiqbench analysis
This research introduces a rigorous framework to audit Large Language Model hypotheses by validating citation integrity and ensuring consistency between predicted biological mechanisms and actual morphological data in longitudinal cell imaging. By applying quantitative tests like V1 (citation validity) and V2 (morphology compatibility), the study establishes an evaluation-first approach that preserves scientific provenance while generating falsifiable narratives from high-dimensional cellular signatures. The work addresses a critical gap in using LLMs for complex biological interpretation, particularly when analyzing subtle effects of chronic perturbations such as low-dose radiation.
Auditing Retrieval-Augmented LLM Hypotheses for Longitudinal Cell Painting Morphology
arXiv:2607.19415v1 Announce Type: cross Abstract: High-content morphological profiling (Cell Painting) yields sensitive, high-dimensional signatures of cellular state, but translating longitudinal morphology trajectories into interpretable biology remains difficult, especially for weak, chronic perturbations such as low-dose-rate ionizing radiation. Large language models (LLMs) can synthesize heterogeneous evidence into biological narratives, yet their scientific use requires quantitative auditing. We present an evaluation-first, retrieval-augmented interpretation framework for longitudinal Cell Painting morphology, applied to a 9-week RPE-1 time course across five dose rates (0.003--6.0 mGy/hr). Week-matched treated-control morphology deltas are combined with retrieved perturbation neighbors, pathway context, and literature evidence through stable evidence identifiers, enabling an LLM to generate structured, evidence-linked hypotheses that are hierarchically summarized while preserving provenance. We introduce two quantitative auditing tests: V1 citation validity, which verifies that cited evidence identifiers exist in the prompt, and V2 proxy-based morphology compatibility, which evaluates consistency between predicted biological processes and the most altered morphology features. In our experiments, V1 detected no invalid evidence references, while V2 showed meaningful morphology compatibility that increased with perturbation strength and was positively associated with an independent morphology drift summary. The framework produces auditable, falsifiable biological hypotheses, including an adaptive phenotype involving metabolic reprogramming and proteostatic stress at lower dose rates (0.003--0.3 mGy/hr). Current limitations include proxy-based evaluation and the lack of ground-truth mechanism labels.
Abstract:High-content morphological profiling (Cell Painting) yields sensitive, high-dimensional signatures of cellular state, but translating longitudinal morphology trajectories into interpretable biology remains difficult, especially for weak, chronic perturbations such as low-dose-rate ionizing radiation. Large language models (LLMs) can synthesize heterogeneous evidence into biological narratives, yet their scientific use requires quantitative auditing. We present an evaluation-first, retrieval-augmented interpretation framework for longitudinal Cell Painting morphology, applied to a 9-week RPE-1 time course across five dose rates (0.003--6.0 mGy/hr). Week-matched treated-control morphology deltas are combined with retrieved perturbation neighbors, pathway context, and literature evidence through stable evidence identifiers, enabling an LLM to generate structured, evidence-linked hypotheses that are hierarchically summarized while preserving provenance. We introduce two quantitative auditing tests: V1 citation validity, which verifies that cited evidence identifiers exist in the prompt, and V2 proxy-based morphology compatibility, which evaluates consistency between predicted biological processes and the most altered morphology features. In our experiments, V1 detected no invalid evidence references, while V2 showed meaningful morphology compatibility that increased with perturbation strength and was positively associated with an independent morphology drift summary. The framework produces auditable, falsifiable biological hypotheses, including an adaptive phenotype involving metabolic reprogramming and proteostatic stress at lower dose rates (0.003--0.3 mGy/hr). Current limitations include proxy-based evaluation and the lack of ground-truth mechanism labels.
Accepted for publication at ACM BCB 2026. This is the author's version. The definitive Version of Record is available at [this https URL](this https URL)
Quantitative Methods (q-bio.QM); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
arXiv:2607.19415 [q-bio.QM]
(or arXiv:2607.19415v1 [q-bio.QM] for this version)
https://doi.org/10.48550/arXiv.2607.19415 arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1145/3807503.3819448 DOI(s) linking to related resources
Full text under the publisher's open licence · 267 words
Related coverage
From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles
arXiv · Sep 30, 2026
Same Encoder, Different Winner: A Paired-View Framework for Cell Painting Encoder Evaluation
arXiv · Sep 14, 2026
Answer Presence Drives RAG Rewriting Gains
arXiv · Aug 5, 2026
Answer Presence Drives RAG Rewriting Gains
arXiv · Jun 6, 2026