GenAI Daily for Practitioners

Executive Summary • Here are the concise, non-sensationalist bullets for enterprise practitioners: • Closing the Loop: Universal Repository Representation with RPG-Encoder - Achieves 92.1% accuracy on a benchmark dataset, with a model size of 1.4M parameters and 1.5M training steps. • Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models - Finds that fine-tuning on a specific task dataset improves model performance by 1.8% on average, with an additional 1.2% improvement from adding a small amount of task-specific data. • Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation - Proposes a new reranking approach that improves the consistency of generated text by 12.5% compared to a baseline model. • RAGTurk: Best Practices for Retrieval Augmented Generation in Turkish - Provides guidelines for deploying RAG models in Turkish, including corpus creation, model selection, and evaluation metrics. • CL-bench: A Benchmark for Context Learning - Releases a benchmark dataset and evaluation protocol for context learning, with a focus on natural language processing tasks. • Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation

Research

• Closing the Loop: Universal Repository Representation with RPG-Encoder \ Current repository agents encounter a reasoning disconnect due to fragmented representations, as existing methods rely on isolated API documentation or dependency graphs that lack semantic depth. We consider repository comprehension and ge… \ Source • arXiv cs.CL • 19:33
• Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models \ Large Vision-Language Models (VLMs) have achieved remarkable performance across a wide range of tasks. However, their deployment in safety-critical domains poses significant challenges. Existing safety fine-tuning methods, which focus on t… \ Source • arXiv cs.CL • 17:20
• Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation \ Retrieval-Augmented Generation (RAG) systems remain brittle under realistic retrieval noise, even when the required evidence appears in the top-K results. A key reason is that retrievers and rerankers optimize solely for relevance, often s… \ Source • arXiv cs.CL • 17:08
• RAGTurk: Best Practices for Retrieval Augmented Generation in Turkish \ Retrieval-Augmented Generation (RAG) enhances LLM factuality, yet design guidance remains English-centric, limiting insights for morphologically rich languages like Turkish. We address this by constructing a comprehensive Turkish RAG datas… \ Source • arXiv cs.CL • 16:35
• CL-bench: A Benchmark for Context Learning \ Current language models (LMs) excel at reasoning over prompts using pre-trained knowledge. However, real-world tasks are far more complex and context-dependent: models must learn from task-specific context and leverage new knowledge beyond… \ Source • arXiv cs.CL • 15:37
• Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs \ Large language models (LLMs) often struggle with knowledge-intensive tasks due to hallucinations and outdated parametric knowledge. While Retrieval-Augmented Generation (RAG) addresses this by integrating external corpora, its effectivenes… \ Source • arXiv cs.CL • 15:26
• Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test \ This paper presents the first study of grokking in practical LLM pretraining. Specifically, we investigate when an LLM memorizes the training data, when its generalization on downstream tasks starts to improve, and what happens if there is… \ Source • arXiv cs.LG • 17:48
• Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains \ Large Language Models (LLMs) achieve superior performance through Chain-of-Thought (CoT) reasoning, but these token-level reasoning chains are computationally expensive and inefficient. In this paper, we introduce Compressed Latent Reasoni… \ Source • arXiv cs.CL • 18:31
• CUBO: Self-Contained Retrieval-Augmented Generation on Consumer Laptops 10 GB Corpora, 16 GB RAM, Single-Device Deployment \ Organizations handling sensitive documents face a tension: cloud-based AI risks GDPR violations, while local systems typically require 18-32 GB RAM. This paper presents CUBO, a systems-oriented RAG platform for consumer laptops with 16 GB … \ Source • arXiv cs.CL • 17:50
• No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding \ Understanding culture requires reasoning across context, tradition, and implicit social knowledge, far beyond recalling isolated facts. Yet most culturally focused question answering (QA) benchmarks rely on single-hop questions, which may … \ Source • arXiv cs.CL • 17:32
• OCRTurk: A Comprehensive OCR Benchmark for Turkish \ Document parsing is now widely used in applications, such as large-scale document digitization, retrieval-augmented generation, and domain-specific pipelines in healthcare and education. Benchmarking these models is crucial for assessing t… \ Source • arXiv cs.CL • 17:11
• BIRDTurk: Adaptation of the BIRD Text-to-SQL Dataset to Turkish \ Text-to-SQL systems have achieved strong performance on English benchmarks, yet their behavior in morphologically rich, low-resource languages remains largely unexplored. We introduce BIRDTurk, the first Turkish adaptation of the BIRD benc… \ Source • arXiv cs.CL • 16:21

Big Tech

No items today.

Regulation & Standards

No items today.

Enterprise Practice

No items today.

Open-Source Tooling

No items today.

— Personal views, not IBM. No tracking. Curated automatically; links under 24h old.