AI alignment must move beyond assuming users have fully formed goals and instead provide active cognitive support to help form and refine intent over time.
arXiv:2503.13975
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
CogInstrument represents human reasoning as revisable cognitive motifs in graphical form to support iterative alignment with LLMs during planning tasks, with a N=12 study indicating gains in targeted revision, agency, and trust over standard dialogue interfaces.
LLMs drop 39% in performance during multi-turn conversations due to premature assumptions and inability to recover from early errors.
The paper reduces a broad set of prompt engineering techniques to six core approaches and applies them to life sciences use cases while addressing common LLM pitfalls.
citing papers explorer
-
Alignment has a Fantasia Problem
AI alignment must move beyond assuming users have fully formed goals and instead provide active cognitive support to help form and refine intent over time.
-
CogInstrument: Modeling Cognitive Processes for Bidirectional Human-LLM Alignment in Planning Tasks
CogInstrument represents human reasoning as revisable cognitive motifs in graphical form to support iterative alignment with LLMs during planning tasks, with a N=12 study indicating gains in targeted revision, agency, and trust over standard dialogue interfaces.