Tag
IDEEA proposes a training-free, input-dependent steering method for large language models that clusters activations and uses optimal matching to improve truthfulness in TruthfulQA by up to 23.5% over baselines.
Proposes three attention-guided strategies for layer selection in contrastive decoding for large language models, improving factuality on TruthfulQA over the DoLa baseline.
This paper audits five diversity measures for LLM ensembles, finding that their associations with majority-vote gain are heavily entangled with model capability and are unstable after controlling for capability. The only robust signal is a modest residual pairwise co-failure association.
This paper proposes a multi-factor scoring system for evaluating LLM responses, integrating accuracy, conciseness, factual consistency, readability, and coherence. Applied to the TruthfulQA dataset, it reveals strengths and limitations of mainstream models, offering a transparent evaluation framework.