Exploration of Plan-Guided Summarization for Narrative Texts: the Case of Small Language Models
August 25, 2025admin NUAI,Committee,News,Uncategorized(0)arXiv:2504.09071v2 Announce Type: replace Abstract: Plan-guided summarization attempts to reduce hallucinations in small language models...
Exploiting Adaptive Contextual Masking for Aspect-Based Sentiment Analysis
July 18, 2025admin NUAI,Committee,News,Uncategorized(0)arXiv:2402.13722v2 Announce Type: replace Abstract: Aspect-Based Sentiment Analysis (ABSA) is a fine-grained linguistics problem that...
Explaining Length Bias in LLM-Based Preference Evaluations
September 3, 2025admin NUAI,Committee,News,Uncategorized(0)arXiv:2407.01085v4 Announce Type: replace-cross Abstract: The use of large language models (LLMs) as judges, particularly...
Explaining Large Language Models with gSMILE
October 22, 2025admin NUAI,Committee,News,Uncategorized(0)arXiv:2505.21657v5 Announce Type: replace Abstract: Large Language Models (LLMs) such as GPT, LLaMA, and Claude...
Expanding the WMT24++ Benchmark with Rumantsch Grischun, Sursilvan, Sutsilvan, Surmiran, Puter, and Vallader
September 25, 2025admin NUAI,Committee,News,Uncategorized(0)arXiv:2509.03148v2 Announce Type: replace Abstract: The Romansh language, spoken in Switzerland, has limited resources for...
ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
September 3, 2025admin NUAI,Committee,News,Uncategorized(0)arXiv:2507.14201v2 Announce Type: replace-cross Abstract: We present ExCyTIn-Bench, the first benchmark to Evaluate an LLM...
Exclusive eBook: The great Al hype correction of 2025
February 21, 2026admin NUAI,Committee,News,Uncategorized(0)2025 was a year of reckoning, including how the heads of the top AI companies...
EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes
January 5, 2026admin NUAI,Committee,News,Uncategorized(0)arXiv:2507.11407v2 Announce Type: replace Abstract: This technical report introduces EXAONE 4.0, which integrates a Non-reasoning...
Exa AI Introduces Exa Instant: A Sub-200ms Neural Search Engine Designed to Eliminate Bottlenecks for Real-Time Agentic Workflows
February 14, 2026admin NUAI,Committee,News,Uncategorized(0)In the world of Large Language Models (LLMs), speed is the only feature that matters...
