Synapse combines two-phase dense retrieval with LLM-guided differential evolution to optimize job-candidate alignment, reporting 22% nDCG@10 gains and over 60% relative score improvements.
theory of mind
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7roles
background 1polarities
background 1representative citing papers
A framework distills noisy user logs into rules and preference pairs, clusters them by query and feedback, then fine-tunes either an expert adapter or a critic adapter to improve future responses.
Mind modeling grounds personalization in explicit, revisable attribution of users' mental states via Theory of Mind, enabling more interpretable adaptive systems than traditional behavior-based approaches.
A weighted similarity ensemble unifies user-item and item-item collaborative filtering using shared embeddings to deliver competitive top-N recommendations without extra fine-tuning.
The thesis identifies theoretical, empirical, and conceptual flaws in offline fairness measures for recommender systems and contributes new evaluation methods and practical guidelines.
A multi-agent multimodal system with fact-grounded adjudication and a dynamic two-tier preference graph cuts false positives in content filtering by 74.3% and nearly doubles F1-score versus text-only baselines while supporting user-driven Delta adjustments.
Introduces semantic Pareto-DQN for multi-objective recommendation that sustains trajectory variance to improve diversity and fairness on MovieLens with limited engagement loss.
citing papers explorer
-
Synapse: Evolving Job-Person Fit with Explainable Two-phase Retrieval and LLM-guided Genetic Resume Optimization
Synapse combines two-phase dense retrieval with LLM-guided differential evolution to optimize job-candidate alignment, reporting 22% nDCG@10 gains and over 60% relative score improvements.
-
Improve Large Language Model Systems with User Logs
A framework distills noisy user logs into rules and preference pairs, clusters them by query and feedback, then fine-tunes either an expert adapter or a critic adapter to improve future responses.
-
Mind Modeling: A ToM-Based Framework for Personalization
Mind modeling grounds personalization in explicit, revisable attribution of users' mental states via Theory of Mind, enabling more interpretable adaptive systems than traditional behavior-based approaches.
-
Collaborative Filtering Through Weighted Similarities of User and Item Embeddings
A weighted similarity ensemble unifies user-item and item-item collaborative filtering using shared embeddings to deliver competitive top-N recommendations without extra fine-tuning.
-
Offline Evaluation Measures of Fairness in Recommender Systems
The thesis identifies theoretical, empirical, and conceptual flaws in offline fairness measures for recommender systems and contributes new evaluation methods and practical guidelines.
-
Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent Collaboration
A multi-agent multimodal system with fact-grounded adjudication and a dynamic two-tier preference graph cuts false positives in content filtering by 74.3% and nearly doubles F1-score versus text-only baselines while supporting user-driven Delta adjustments.
-
Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation
Introduces semantic Pareto-DQN for multi-objective recommendation that sustains trajectory variance to improve diversity and fairness on MovieLens with limited engagement loss.