cs.CLNov 19, 2026

What If Chain-of-Thought Is Not Enough?

Authors: Marc Jansen

Organizations: Computer Science Institute, University of Applied Sciences Ruhr West, Bottrop, Germany

Abstract

Reasoning capabilities in large language models have evolved from prompting-based methods to internalized model behaviors. In this paper, we investigate whether the internal thinking model of an LLM can be deliberately changed and whether such a change is beneficial. Instead of relying on Chain-of-Thought, we train models to follow Question--Option--Criteria (QOC), a structured decision process that decomposes a task into explicit questions, competing options, and evaluation criteria. We present a three-generation development pipeline that ranges from a basic QOC decision core to richer answer synthesis and statistically enriched QOC reasoning. We then evaluate the resulting models with respect to both internal consistency and output quality. Across the reported experiments, QOC-based fine-tuning improves answer quality relative to non-fine-tuned base models and yields particularly strong gains once models are large enough to execute the underlying QOC computations reliably. The results suggest that the internal thinking model of an LLM is trainable and that structured alternatives to Chain-of-Thought can provide a promising path toward more reliable, interpretable, and task-adapted decision support.

Figures & tables

Explore similar work

CardsList
  1. Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers

    Mar 2, 2026Kyle Cox, Darius Kianersi, Adrià Garriga-AlonsoFaithfulness of Language Model ExplanationsLLM Interpretability

  2. Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models

    Jul 16, 2026Jungseob Lee, Seungyoon Lee, Suhyune Son +4CoT DistillationLanguage Model Distillation

  3. Large Language Models Decide Early and Explain Later

    Apr 24, 2026Ayan Datta, Zhixue Zhao, Bhuvanesh Verma +3Efficient Language Model ReasoningLLM Inference Acceleration