News
Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
arXiv:2507.00322v1 Announce Type: new Abstract: Despite remarkable advances in coding capabilities, language models (LMs) still...
Exploring the Influence of Relevant Knowledge for Natural Language Generation Interpretability
arXiv:2510.24179v1 Announce Type: new Abstract: This paper explores the influence of external knowledge integration in...
Exploring the Escalation of Source Bias in User, Data, and Recommender System Feedback Loop
arXiv:2405.17998v2 Announce Type: replace-cross Abstract: Recommender systems are essential for information access, allowing users to...
Exploring Procedural Data Generation for Automatic Acoustic Guitar Fingerpicking Transcription
arXiv:2508.07987v1 Announce Type: cross Abstract: Automatic transcription of acoustic guitar fingerpicking performances remains a challenging...
Exploring LLM Autoscoring Reliability in Large-Scale Writing Assessments Using Generalizability Theory
arXiv:2507.19980v1 Announce Type: new Abstract: This study investigates the estimation of reliability for large language...
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...
