Institution profile

Pfizer

Industry researchnorthamerica · us
Official website
Research library19linked papers
Opportunities0open roles
Selected work

Representative Papers

Closed-Loop Knowledge Dynamics: An Operational Framework for Saturation and Escape

Jul 15, 2026

Closed knowledge systems often saturate in performance under internal feedback, hindering sustained improvement. This work proposes a three-layer operational framework that characterizes knowledge evolution through structural parameters θ, leveraging tools such as transition kernels, Lyapunov drift conditions, and lower bounds on KL divergence to analyze attractor dynamics within fixed structures and structural transitions induced by external interventions. The study innovatively constructs a falsifiable mechanism for structural intervention, establishing an operational link among system stability, measurable intervention effects, and cross-domain diagnostics, while revealing why conditional mutual information fundamentally fails to verify “escape” phenomena. Empirical validation across large language model code repair, sparse-reward reinforcement learning, and Bayesian optimization demonstrates that feedback intensity and alignment critically govern quality-enhancing escapes, clarifying their theoretical preconditions.

0 citationsRead paper

Optimizing Large Language Models for Causality Assessment in Pharmacovigilance: Developing a Performance Metric as Objective for Bayesian Hyperparameter Optimization

Jul 04, 2026

This study addresses the suboptimal performance of large language models (LLMs) in causality assessment for automated pharmacovigilance and the absence of effective methods for optimizing inference hyperparameters such as temperature. To this end, the authors propose a Gaussian process–based Bayesian optimization framework that systematically tunes temperature for LLM-based causal inference, incorporating a novel weighted consistency metric—particularly the Entropy-Weighted Agreement Consistency Score (EWACS). Evaluated on individual case safety reports from FAERS using GPT-5.2, chain-of-thought prompting, and four consistency measures, the approach significantly improves agreement between model predictions and expert judgments from 45.0% to 72.0%, with a 42.9-percentage-point gain in the “suspected” category. These results demonstrate that optimal temperature is highly context-dependent, precluding a universal setting, and substantially enhance the practical utility of LLMs in regulatory pharmacovigilance applications.

0 citationsRead paper

BayesEvolve: Explicit Belief States for Autonomous Scientific Discovery

Jun 29, 2026

This work addresses a critical limitation in existing autonomous scientific discovery systems, which often rely on experimental memory or heuristic summarization and lack explicit, uncertainty-aware modeling of belief over hypothesis quality. To overcome this, the authors propose BayesEvolve, a novel framework that integrates Bayesian inference with large language models to construct an updatable predictive belief state that actively guides experimental design. Central to this approach is a belief-guided selection mechanism incorporating annealed uncertainty-aware rewards, which substantially improves sample efficiency under a fixed evaluation budget. Empirical results demonstrate that the learned belief state effectively predicts the quality of candidate hypotheses and enables efficient late-stage focused exploration, thereby accelerating the discovery process.

0 citationsRead paper
Recent publications

Latest Papers

Closed-Loop Knowledge Dynamics: An Operational Framework for Saturation and Escape

Jul 15, 2026

Closed knowledge systems often saturate in performance under internal feedback, hindering sustained improvement. This work proposes a three-layer operational framework that characterizes knowledge evolution through structural parameters θ, leveraging tools such as transition kernels, Lyapunov drift conditions, and lower bounds on KL divergence to analyze attractor dynamics within fixed structures and structural transitions induced by external interventions. The study innovatively constructs a falsifiable mechanism for structural intervention, establishing an operational link among system stability, measurable intervention effects, and cross-domain diagnostics, while revealing why conditional mutual information fundamentally fails to verify “escape” phenomena. Empirical validation across large language model code repair, sparse-reward reinforcement learning, and Bayesian optimization demonstrates that feedback intensity and alignment critically govern quality-enhancing escapes, clarifying their theoretical preconditions.

0 citationsRead paper

Optimizing Large Language Models for Causality Assessment in Pharmacovigilance: Developing a Performance Metric as Objective for Bayesian Hyperparameter Optimization

Jul 04, 2026

This study addresses the suboptimal performance of large language models (LLMs) in causality assessment for automated pharmacovigilance and the absence of effective methods for optimizing inference hyperparameters such as temperature. To this end, the authors propose a Gaussian process–based Bayesian optimization framework that systematically tunes temperature for LLM-based causal inference, incorporating a novel weighted consistency metric—particularly the Entropy-Weighted Agreement Consistency Score (EWACS). Evaluated on individual case safety reports from FAERS using GPT-5.2, chain-of-thought prompting, and four consistency measures, the approach significantly improves agreement between model predictions and expert judgments from 45.0% to 72.0%, with a 42.9-percentage-point gain in the “suspected” category. These results demonstrate that optimal temperature is highly context-dependent, precluding a universal setting, and substantially enhance the practical utility of LLMs in regulatory pharmacovigilance applications.

0 citationsRead paper

BayesEvolve: Explicit Belief States for Autonomous Scientific Discovery

Jun 29, 2026

This work addresses a critical limitation in existing autonomous scientific discovery systems, which often rely on experimental memory or heuristic summarization and lack explicit, uncertainty-aware modeling of belief over hypothesis quality. To overcome this, the authors propose BayesEvolve, a novel framework that integrates Bayesian inference with large language models to construct an updatable predictive belief state that actively guides experimental design. Central to this approach is a belief-guided selection mechanism incorporating annealed uncertainty-aware rewards, which substantially improves sample efficiency under a fixed evaluation budget. Empirical results demonstrate that the learned belief state effectively predicts the quality of candidate hypotheses and enables efficient late-stage focused exploration, thereby accelerating the discovery process.

0 citationsRead paper