Length Penalties Make Chain-of-Thought Less Monitorable

Abstract

To curb overthinking and reduce inference costs, researchers now train reasoning models with penalties on chain of thought length. We find that these penalties degrade monitorability. Shorter chains of thought mention misleading hints less often, but the hints still influence the models' answers. We train Qwen3 4B and Qwen3 14B to produce different target chain lengths, then evaluate them using biasing hint interventions on held out MMLU Pro R data and four transfer benchmarks. Compression reduces reasoning tokens and preserves most multiple choice accuracy, while hint influence remains near baseline. At the shortest target chain length, lower bound faithfulness drops to 63.1 percent of baseline for Qwen3 14B and 69.4 percent for Qwen3 4B. The monitor's raw hint detection rate falls from 69 percent to 49 percent and from 60 percent to 48 percent, respectively. To separate length from content, we randomly delete sentences from uncompressed baseline chains until the remaining text matches the compressed length. Across both Qwen3 model sizes and all five evaluation distributions, compressed chains still mention the hint 7 to 35 percentage points less often than these length matched baselines. We therefore identify a compression and monitorability frontier where reducing reasoning costs removes more evidence than shorter traces alone would predict.