Retrieval-Augmented Generation on Tolga Dimlioglu

Retrieval-Augmented Generation on Tolga Dimliogluhttps://tolgadimli.github.io/tags/retrieval-augmented-generation/Recent content in Retrieval-Augmented Generation on Tolga DimliogluHugo -- 0.147.2enTue, 18 Nov 2025 00:00:00 +0000Streamlining Industrial Contract Management with Retrieval-Augmented LLMshttps://tolgadimli.github.io/indcollab/data1/Tue, 18 Nov 2025 00:00:00 +0000https://tolgadimli.github.io/indcollab/data1/A modular retrieval-augmented LLM framework for automating contract revision analysis and optimization under low-resource, real-world industrial settings.Streamlining Industrial Contract Management with Retrieval-Augmented LLMshttps://tolgadimli.github.io/papers/paper1/Sat, 15 Nov 2025 00:00:00 +0000https://tolgadimli.github.io/papers/paper1/We propose a retrieval-augmented LLM system that automatically identifies and rewrites problematic industrial contract revisions, achieving high accuracy even in low-resource legal settings.GRAWA: Gradient-based Weighted Averaging for Distributed Training of Deep Learning Modelshttps://tolgadimli.github.io/papers/paper4/Fri, 15 Mar 2024 00:00:00 +0000https://tolgadimli.github.io/papers/paper4/We introduce gradient-norm–weighted averaging methods for distributed deep learning that pull workers toward flatter regions of the loss landscape. The proposed model-level and layer-level variants converge in both convex and non-convex settings and empirically achieve faster training, better optima, and reduced communication compared to prior work.