The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It

Documenti analoghi

• Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey
  di: Mondorf, Philipp, et al.
  Pubblicazione: (2024)
• How Language Models Conflate Logical Validity with Plausibility: A Representational Analysis of Content Effects
  di: Bertolazzi, Leonardo, et al.
  Pubblicazione: (2025)
• Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning
  di: Mondorf, Philipp, et al.
  Pubblicazione: (2024)
• LogicSkills: A Structured Benchmark for Formal Reasoning in Large Language Models
  di: Rabern, Brian, et al.
  Pubblicazione: (2026)
• A Systematic Analysis of Large Language Models as Soft Reasoners: The Case of Syllogistic Inferences
  di: Bertolazzi, Leonardo, et al.
  Pubblicazione: (2024)