ข่าว
Exploring Cross-Lingual Knowledge Transfer via Transliteration-Based MLM Fine-Tuning for Critically Low-resource Chakma Language
arXiv:2510.09032v1 Announce Type: new Abstract: As an Indo-Aryan language with limited available data, Chakma remains...
Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm
arXiv:2509.23946v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) and its variants have markedly advanced the reasoning...
Exploration of Plan-Guided Summarization for Narrative Texts: the Case of Small Language Models
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
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
arXiv:2407.01085v4 Announce Type: replace-cross Abstract: The use of large language models (LLMs) as judges, particularly...
Explaining Large Language Models with gSMILE
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
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
arXiv:2507.14201v2 Announce Type: replace-cross Abstract: We present ExCyTIn-Bench, the first benchmark to Evaluate an LLM...
Everything you need to know about estimating AI’s energy and emissions burden
When we set out to write a story on the best available estimates for AI’s...
Everyone’s looking to get in on vibe coding — and Google is no different with Stitch, its follow-up to Jules
Google is looking to compete in vibe coding with Stitch, which designs user interfaces (UIs)...
Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model
arXiv:2510.18855v2 Announce Type: replace Abstract: We present Ring-1T, the first open-source, state-of-the-art thinking model with...
EventHunter: Dynamic Clustering and Ranking of Security Events from Hacker Forum Discussions
arXiv:2507.09762v1 Announce Type: cross Abstract: Hacker forums provide critical early warning signals for emerging cybersecurity...
