Closed-system multi-step LLM reasoning is subject to an information-theoretic bound where mutual information with evidence decreases, preserving accuracy while eroding faithfulness, with EGSR recovering it on SciFact and FEVER.
Olson, Yoshua Bengio, and Karim Jerbi
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Interviews reveal a four-stage vibe coding workflow that accelerates prototyping while introducing tensions between quick efficiency and reflective design intention, plus asymmetries in trust and ownership.
citing papers explorer
-
The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning
Closed-system multi-step LLM reasoning is subject to an information-theoretic bound where mutual information with evidence decreases, preserving accuracy while eroding faithfulness, with EGSR recovering it on SciFact and FEVER.
-
Vibe Coding in Product Teams: Reconfiguring AI-Assisted Workflows, Prototyping, and Collaboration
Interviews reveal a four-stage vibe coding workflow that accelerates prototyping while introducing tensions between quick efficiency and reflective design intention, plus asymmetries in trust and ownership.