Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally

arXiv:2610.21204v1 Announce Type: new Abstract: When a speaker says ``some students passed'', listeners infer that not all of them did. Reasoning models now let users decide how long a model thinks before it answers, but we do not know what extra thinking does to such everyday inferences. We study this directly: we keep a model's weights fixed, change only how much it thinks, and record which reading it chooses. A second tool cuts the model's own reasoning at successive points and asks for an answer, showing where the reading changes. Thinking makes models read logical words as logic: it cancels the implicatures of some (not all) and or (not both) in most tested open reasoning models and in GPT-5, while context-driven inferences such as indirect answers improve. The trace shows why: models first entertain the enriched reading and cancel it later. Answering from that early reading, an exploratory inference-time remedy, recovers these implicatures without losing literal accuracy. Evaluations of reasoning models should measure how they interpret, not only how accurate they are.

Related

• The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
• Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
• Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction

Source: arXiv cs.AI | 2026-10-16