Mean-difference residual stream injections outperform personality prompting for OCEAN trait steering in most LLMs, with hybrids performing best and showing approximate linearity but non-human trait covariances.
Transactions of the ACL 7, 625–641 (2019)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Task prompt vectors, formed by subtracting random initialization from tuned soft prompts, support low-resource initialization and arithmetic combination across tasks on 12 NLU datasets while remaining independent of initialization seed on two model architectures.
PEFT-Bench is a standardized end-to-end benchmark for 7 PEFT methods across 27 NLP datasets on autoregressive LLMs, accompanied by the PSCP metric that penalizes based on trainable parameters, inference speed, and training memory.
ToxiShield delivers a real-time GitHub extension with a BERT toxicity detector at 98% accuracy, a Claude-based coach, and a fine-tuned Llama reframer at 95% style transfer accuracy, validated by a 10-person TAM study.
PEFT-Factory supplies a ready-to-use, extensible codebase that unifies 19 PEFT methods and evaluation pipelines for fine-tuning large autoregressive language models.
Reproducibility study confirms AlphaEdit on original setups but finds performance degrades at high edit counts, fails to generalize to newer models, and harms downstream tasks.
citing papers explorer
-
Reproducibility Study of "AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models"
Reproducibility study confirms AlphaEdit on original setups but finds performance degrades at high edit counts, fails to generalize to newer models, and harms downstream tasks.