#semantic analysis

try —

3 papers match

cs.CR2026

DataShield: Uncovering Risky Fine-Tuning Data Across LLMs Through Consensus Subspace Alignment

Zefeng Wu, Weiwei Qi, Jielong Chen +6

The paper introduces DataShield, a framework that detects risky fine‑tuning data for large language models by aligning safety‑critical semantic subspaces across multiple safety‑ali…

#large language models#fine-tuning#safety assessment#risk detection

cs.DL2026

Research Novelty in Information Systems Journals After ChatGPT: Differences Across Institutional Language Contexts

Ali Safari, Sahar Babaei

The paper investigates how the semantic novelty of articles in top Information Systems journals changed after ChatGPT became widely available, finding a larger decline in novelty f…

#research novelty#large language models#semantic analysis#institutional language context

cs.SE2026

Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs

Xiaoning Ren, Yinxing Xue, Lei Ma +1

The paper presents Code-MUE, a black‑box method that measures the uncertainty of code‑generating large language models by building execution‑based semantic interaction graphs and c…

#code generation#large language models#uncertainty estimation#semantic analysis