LLM-Assisted Abstract Screening with OLIVER: Evaluating Calibration and Single-Model vs. Actor-Critic Configurations in Literature Reviews

TL;DR

This paper introduces OLIVER, an open-source LLM-assisted screening pipeline, evaluates multiple models and configurations across systematic reviews, and finds that actor-critic frameworks enhance screening accuracy and calibration over single models.

Contribution

The study presents OLIVER, compares LLM configurations, and demonstrates that actor-critic models improve screening performance and calibration in literature reviews.

Findings

Model performance varies widely across reviews.

Actor-critic framework improves discrimination and calibration.

Calibration remains weak in single-model setups.

Abstract

Introduction: Recent work suggests large language models (LLMs) can accelerate screening, but prior evaluations focus on earlier LLMs, standardized Cochrane reviews, single-model setups, and accuracy as the primary metric, leaving generalizability, configuration effects, and calibration largely unexamined. Methods: We developed OLIVER (Optimized LLM-based Inclusion and Vetting Engine for Reviews), an open-source pipeline for LLM-assisted abstract screening. We evaluated multiple contemporary LLMs across two non-Cochrane systematic reviews and performance was assessed at both the full-text screening and final inclusion stages using accuracy, AUC, and calibration metrics. We further tested an actor-critic screening framework combining two lightweight models under three aggregation rules. Results: Across individual models, performance varied widely. In the smaller Review 1 (821 abstracts, 63 final includes), several models achieved high sensitivity for final includes but at the cost of substantial false positives and poor calibration. In the larger Review 2 (7741 abstracts, 71 final includes), most models were highly specific but struggled to recover true includes, with prompt design influencing recall. Calibration was consistently weak across single-model configurations despite high overall accuracy. Actor-critic screening improved discrimination and markedly reduced calibration error in both reviews, yielding higher AUCs. Discussion: LLMs may eventually accelerate abstract screening, but single-model performance is highly sensitive to review characteristics, prompting, and calibration is limited. An actor-critic framework improves classification quality and confidence reliability while remaining computationally efficient, enabling large-scale screening at low cost.