conftrace_

model intervention

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) activation steering (1) knowledge localization (1) causal abstraction (1) concept editing (1) neural network (1) high-level concept (1) activation engineering (1) concept leakage (1) code-mixed generation (1)

Papers

Competence Collapse in Code-Mixed Generation: Spectral Evidence and Mechanistic Recovery via Cross-Lingual Activation Steering EACL 2026 Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models ACL 2025 Temporal Alignment of Time Sensitive Facts with Activation Engineering EMNLP 2025 Tuning-Free Accountable Intervention for LLM Deployment – a Metacognitive Approach AAAI 2025 pyvene: A Library for Understanding and Improving PyTorch Models via Interventions NAACL 2024 Addressing Leakage in Concept Bottleneck Models NeurIPS 2022 LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models EMNLP 2022 Concept Bottleneck Models ICML 2020