Preprint2025
Sharp: Steering hallucination in lvlms via representation engineering
Unknown
SHARP is a representation-level intervention framework that modulates hallucination in LVLMs by steering internal representations.
0Jan 1, 2025
AI Research
AI & ML Research Papers
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
All Papers
6 papersPreprint2026
Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations
Pere Martra, Eugenio Martínez Cámara, Alfonso Ureña López
Fairness Pruning introduces a lightweight structural intervention that locates demographic bias in GLU-MLP layers by zeroing at most 40 neurons, achieving 99.49% capability retention while destabilizing bias bidirectionally.
0Jul 30, 2026Large Language ModelsPrompting
arXiv
PreprintEuropean Journal of Cancer Care2011
Benchmarking modern multiprocessors
Kai Li, Christian Bienia
This paper analyzes how pre-intervention exercise habits and baseline depression levels predict adherence, contamination, and dropout rates in walking and control groups.
1.0kJan 1, 2011Benchmarks
JournalTrends in Pharmacological Sciences2021
Network pharmacology: curing causal mechanisms instead of treating symptoms
Cristian Nogales, Zeinab M. Mamdouh, Markus List, et al.
Network pharmacology replaces the one disease-one target-one drug dogma with causal multitarget signaling modules for precise, curative intervention.
1.2kDec 9, 2021
PreprintarXiv.org2024
Controllable Text Generation for LLMs
Xun Liang, Hanyu Wang, Yezhaohui Wang, et al.
A systematic review of controllable text generation for LLMs, defining core concepts, categorizing tasks, and analyzing methods including model retraining, fine-tuning, and decoding-time intervention.
85Aug 22, 2024Large Language ModelsFine Tuning
arXiv
Preprint2026
Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity
Hongnan Ma, Yiwei Shi, Mengyue Yang, et al.
Introduces TimePNS, a necessity-aware framework for time-series explanation that uses counterfactual interventions to identify subsequences essential for model predictions.
0Jul 23, 2026Benchmarks
arXiv