Inclusion-of-Thoughts: Mitigating Preference Instability via Purifying the Decision Space
This addresses the problem of preference instability in LLMs for evaluators and users of multiple-choice benchmarks, though it appears incremental as it builds on existing chain-of-thought methods.
The paper tackles the problem of large language models (LLMs) being vulnerable to plausible distractors in multiple-choice questions, which causes unstable preferences and oscillations between correct and incorrect answers. The result is that their proposed Inclusion-of-Thoughts (IoT) method substantially boosts chain-of-thought performance across arithmetic, commonsense reasoning, and educational benchmarks with minimal computational overhead.
Multiple-choice questions (MCQs) are widely used to evaluate large language models (LLMs). However, LLMs remain vulnerable to the presence of plausible distractors. This often diverts attention toward irrelevant choices, resulting in unstable oscillation between correct and incorrect answers. In this paper, we propose Inclusion-of-Thoughts (IoT), a progressive self-filtering strategy that is designed to mitigate this cognitive load (i.e., instability of model preferences under the presence of distractors) and enable the model to focus more effectively on plausible answers. Our method operates to reconstruct the MCQ using only plausible option choices, providing a controlled setting for examining comparative judgements and therefore the stability of the model's internal reasoning under perturbation. By explicitly documenting this filtering process, IoT also enhances the transparency and interpretability of the model's decision-making. Extensive empirical evaluation demonstrates that IoT substantially boosts chain-of-thought performance across a range of arithmetic, commonsense reasoning, and educational benchmarks with minimal computational overhead.