ROUGE-L Score
PulseAugur coverage of ROUGE-L Score — every cluster mentioning ROUGE-L Score across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New method uses instruction-tuned LLMs to generate BPMN diagrams
Researchers have developed InstruBPM, a method for instruction-tuning open-weight language models to generate Business Process Model and Notation (BPMN) diagrams from natural language descriptions. This approach uses pa…
-
RAG system enhances stock market info retrieval with high accuracy and speed
Researchers have developed a Retrieval-Augmented Generation (RAG) system to improve the accuracy and speed of stock market information retrieval. This system combines retrieval and generative AI techniques to provide mo…
-
New RCR method optimizes KV cache for multimodal AI generation
Researchers have developed a new method called Rate-Controlled Refresh (RCR) to improve the efficiency of KV cache compression in long-form multimodal generation. Traditional methods select visual tokens once at the beg…
-
New multilingual dataset enhances AI crisis warning generation
Researchers have developed CrisiLangs, a new multilingual dataset designed to improve crisis warning generation by language models. This resource extends the existing CrisiText dataset to include warning messages for cr…
-
Qwen3-8B model enhanced for multilingual QA tasks
Researchers have developed a method for multilingual instruction tuning to improve open-ended question answering. Their approach adapts the Qwen3-8B model using LoRA and two multilingual datasets: EuroAlpaca and CrossEu…
-
New benchmark and model advance multilingual patent translation
Researchers have introduced PatMT2, a two-stage domain adaptation pipeline for multilingual patent translation, improving upon existing models like Hy-MT2-7B and Qwen3-32B. This adaptation process enhances translation q…
-
New RAGScope protocol aims to reduce hallucination triage costs
Researchers have developed RAGScope, a new protocol designed to efficiently triage hallucinations in retrieval-augmented generation (RAG) systems. This protocol aims to reduce costs by using a leakage-controlled, eviden…
-
AI fine-tuned for authentic radiology report style
Researchers have developed a method to improve the stylistic alignment of AI-generated radiology reports with those written by human radiologists. By analyzing 2,000 reports from the CheXpert Plus dataset, they identifi…
-
New NLP task Narrative Consolidation unifies multi-perspective accounts
Researchers have introduced a new natural language processing task called Narrative Consolidation, which focuses on unifying multi-perspective accounts into a single, coherent, and chronologically accurate text. Unlike …
-
Sign Language Translation Models Overestimated Due to Signer Dependence
A new research paper published on arXiv highlights significant overestimation in the evaluation of sign language translation (SLT) models. The study found that current evaluation methods, which often include overlapping…
-
LLMs show promise in extracting software design decisions from code commits
A preliminary study explored the ability of four Large Language Models (LLMs) to extract Architectural Design Decisions (ADDs) from source code commits. Models including Gemini 3-Pro, DeepSeek-R1, Kimi K2, and Qwen3 wer…
-
New LUX architecture enhances explainable endoscopic image captioning
Researchers have developed LUX, a novel graph-conditioned vision-language architecture designed for explainable endoscopic image captioning. This system addresses the limitations of current deep learning models by const…
-
New Denoising-Aware Inversion Method Exposes Privacy Risks in Noisy Text Embeddings
Researchers have developed a new method called Denoising-Aware Inversion (DAEI) to address privacy risks in text embeddings that have been protected by adding Gaussian noise. Standard inversion attacks struggle with the…
-
New framework enables extensible LLM instruction tuning without retraining
Researchers have developed SemiAdapt-Instruct, a novel framework for instruction-tuning large language models (LLMs). This modular system addresses the challenge of adapting fine-tuned models to evolving domains without…
-
New AI frameworks CANOE and CoPlan enhance care planning transparency
Researchers have introduced two novel AI frameworks, CANOE and CoPlan, designed to enhance transparency and safety in complex care plan coordination. CANOE, a multi-agent neuro-symbolic system, utilizes an argumentative…
-
LLMs fail to translate Korean Braille, study finds
A new research paper reveals significant accessibility failures in state-of-the-art Large Language Models (LLMs) when it comes to translating Korean Braille. Despite expectations that these models could handle Braille t…
-
New RLHF framework improves Vietnamese translation of historical manuscripts
Researchers have developed a new multimodal Reinforcement Learning from Human Feedback (RLHF) framework to translate historical Han-Nom manuscripts into modern Vietnamese. This approach leverages both the visual informa…
-
AI models advance ad headline generation with improved CTR and quality · 2 sources tracked
Two new research papers propose advanced methods for generating advertising headlines. One paper introduces COBART, a controlled, optimized, bidirectional, and auto-regressive Transformer model that uses prefix control …
-
New ARKD framework enhances LLM compression via adaptive KL divergence
Researchers have developed ARKD, a novel knowledge distillation framework designed to improve the compression and performance of large language models (LLMs). This adaptive reinforcement learning-guided approach dynamic…
-
New research explores GPU-free and gradient-based LLM hallucination detection
Two new research papers explore methods for detecting hallucinations in large language models (LLMs). The first paper, "How Far Can You Get Without a GPU?", benchmarks lightweight, CPU-feasible methods for hallucination…