The paper reports that chain-of-thought features extracted by sparse autoencoders and transferred through activation patching improve answer confidence in Pythia-2.8B but not in Pythia-70M, implying a scale threshold for CoT faithfulness.
Probing Language Models on Their Knowledge Source
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Large Language Models (LLMs) often encounter conflicts between their learned, internal (parametric knowledge, PK) and external knowledge provided during inference (contextual knowledge, CK). Understanding how LLMs models prioritize one knowledge source over the other remains a challenge. In this paper, we propose a novel probing framework to explore the mechanisms governing the selection between PK and CK in LLMs. Using controlled prompts designed to contradict the model's PK, we demonstrate that specific model activations are indicative of the knowledge source employed. We evaluate this framework on various LLMs of different sizes and demonstrate that mid-layer activations, particularly those related to relations in the input, are crucial in predicting knowledge source selection, paving the way for more reliable models capable of handling knowledge conflicts effectively.
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
The paper reports that chain-of-thought features extracted by sparse autoencoders and transferred through activation patching improve answer confidence in Pythia-2.8B but not in Pythia-70M, implying a scale threshold for CoT faithfulness.