Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation

Documenti analoghi

• Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs
  di: Cheng, Ziling, et al.
  Pubblicazione: (2025)
• PreSumm: Predicting Summarization Performance Without Summarizing
  di: Koniaev, Steven, et al.
  Pubblicazione: (2025)
• Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations
  di: Yu, Lei, et al.
  Pubblicazione: (2024)
• Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought
  di: Ramji, Keshav, et al.
  Pubblicazione: (2026)
• Can LLMs Solve longer Math Word Problems Better?
  di: Xu, Xin, et al.
  Pubblicazione: (2024)