Encoder-based transformers DeBERTa, RoBERTa, and BART show no evidence of capturing the M-Heuristic pragmatic distinction between lexical causatives such as "Larry stopped the car" and periphrastic ca…
The YNU-HPCC team placed in subtask A of SemEval-2025 Task 11 with a RoBERTa-based system that scored an official ranking score of 0.44 across all languages, according to the team's arXiv paper. The t…
A modular transformer-based framework detects and structures social tipping point evidence at the passage level in climate documents, according to an arXiv paper (arXiv:2609.12254v1). The framework co…
A security engineering perspective on deploying large language models (LLMs) into production outlines a tripartite architecture for AI guardrails, including input sanitization, model alignment, and ou…
Researchers propose EmoLASP, a framework combining language models with Answer Set Programming to predict VAD scores in conversations, improving performance over using language models alone on the IEM…
A new audit framework, the Cross-Platform Fairness Evaluation (CPFE), applied to four transformer models (BERT, RoBERTa, Emotion-DistilRoBERTa, GoEmotions-RoBERTa) trained on a Kaggle mental health co…
A new arXiv study (2608.20371v1) comparing zero-shot Claude Haiku against fine-tuned NLU models for intent detection finds that fine-tuned RoBERTa beats Claude by 11.8 points on ATIS (95.9 vs. 84.1, p…
Researchers propose TH-GNN, a heterogeneous temporal graph neural network that detects LLM-agent shilling attacks on recommender systems by jointly modeling temporal, structural, and semantic signals.…
A study submitted to arXiv on 2 Jun 2026 compares transformer models BERT, RoBERTa, and BART for text summarization, examining their architectures, pretraining strategies, and suitability for extracti…
ColBERT-style multi-vector models, such as colbert-ir/colbertv2.0, are now integrated into the sentence-transformers library, enabling high-precision RAG pipelines through late interaction and MaxSim …
A sentiment analysis of 32,000 Hacker News posts and 340,000 comments finds that nearly 65% of posts have negative sentiment, and these negative posts average 35.6 points, a 27% premium over the overa…
A new study from arXiv preprint 2607.24797v1 finds that decoder-only large language models (LLMs) such as GPT-2, OPT, and Pythia entangle reading and writing into a single code, unlike the human brain…
A team of researchers achieved an average precision of 0.875 and a macro-F1 of 0.72 on the Ambivalence/Hesitancy Video Recognition Challenge of the 11th ABAW Competition using an audio-text system tha…
A new study finds that a plain, fully fine-tuned RoBERTa model matches or surpasses specialized AI-generated text detectors across benchmarks, challenging the industry's focus on architectural complex…
Researchers submitted a system to SemEval-2026 Task 9 for detecting multilingual online polarization using transformer-based models with class weighting and threshold tuning. Their approach achieved c…
Researchers at arXiv found that using large language models (LLMs) like GPT-5.2 to label training data for entity matching can reduce manual labeling effort by hundreds of hours, with student models p…
A user submitted a fake AI-generated article to Hacker News, which was flagged after detection. Testing local AI detectors on a 2013 Paul Graham essay showed it was rated as more likely AI-generated t…
Researchers introduced HierBias, a hierarchical context-conditioned media bias detector that models document context to improve sentence-level bias classification. The system achieved 0.853 F1 and 0.7…
A paper by Saha et al. (arXiv 2506.07001) demonstrates that detector-guided paraphrasing using RoBERTa as a reward reduces the true positive rate of AI-generated text detectors by 87.88% across Binocu…
Researchers at the University of Washington and Allen Institute for AI conducted the first fine-grained study of narrative features in Dolma, a 3-trillion-token open LLM pretraining corpus. They devel…