Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Computation and Language
arXiv:2609.03366 (cs)
[Submitted on 3 Sep 2026]
Title:Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT
View a PDF of the paper titled Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT, by Zikai Zhou and 5 other authors
View PDF
HTML (experimental)
Abstract:Accountability means a decision can be examined, justified, and contested. LLMs make this hard: fluent output may be ungrounded, incomplete, or unfaithful to the decision process. Achieving accountability requires verified rationales (how was the decision reached), assumptions (what was assumed rather than known), policy consistency (the same treatment for the same facts), and pivotal conditions (what would change the outcome). We introduce self-faithfulness as an automatic test of accountability: changing the pivotal conditions should change the decision.
We examine accountable AI through clinical trial matching, a high-stakes task central to evidence-based medicine. Although LLM-based matchers match patients to trials reasonably accurately, they apply decision policies inconsistently and produce rationales that are unfaithful to their own decisions.
We introduce VERDICT, an LLM-based agent that translates a decision task, its constraints, and its policy into Satisfiability Modulo Theories (SMT), then derives the decision with SMT and MaxSMT solvers -- so policies are applied consistently and decisions are accountable by construction.
Across a SIGIR 2016-derived dataset and TREC 2021, VERDICT achieves the strongest decision accuracy among LLM-only and neurosymbolic baselines, applies policies with perfect consistency, and produces clinician-preferred rationales grounded in explicit assumptions and pivotal conditions, with improved counterfactual self-faithfulness.
| Comments: | Accepted to EMNLP 2026 (Main Conference). 46 pages, 6 figures, 28 tables. Code and prompts: this https URL |
| Subjects: | Computation and Language (cs.CL); Computers and Society (cs.CY); Logic in Computer Science (cs.LO) |
| ACM classes: | I.2.7; I.2.4; J.3 |
| Cite as: | arXiv:2609.03366 [cs.CL] |
| (or arXiv:2609.03366v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.03366
arXiv-issued DOI via DataCite (pending registration)
|
Full-text links:
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
View a PDF of the paper titled Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT, by Zikai Zhou and 5 other authors
Current browse context:
cs.CL
References & Citations
Loading...
Bookmark
Bibliographic Tools
Code, Data, Media
Demos
Related Papers
About arXivLabs
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.