Han Wang
Publications
The Detection--Extraction Gap: Models Know the Answer Before They Can Say It
Modern reasoning models continue generating long after the answer is already determined. Across five model configurations, two families, and three benchmarks, we find that \textbf{52--88\% of chain-of-thought tokens are produced after the answer is recoverable} from a partial prefix. This post-commitment generation reveals a structural phenomenon: the \textbf{detection--extraction gap}. Free continuations from early prefixes recover the correct answer even at 10\% of the trace, while forced extraction fails on 42\% of these cases. The answer is recoverable from the model state, yet prompt-conditioned decoding fails to extract it. We formalize this mismatch via a total-variation bound between free and forced continuation distributions, yielding quantitative estimates of suffix-induced shift. Exploiting this asymmetry, we propose Black-box Adaptive Early Exit (\BAEE{}), which uses free continuations for both detection and extraction, truncating \textbf{70--78\% of serial generation} while \textbf{improving accuracy by 1--5\,pp} across all models. For thinking-mode models, early exit prevents post-commitment overwriting, yielding gains of up to 5.8\,pp; a cost-optimized variant achieves 68--73\% reduction at a median of 9 API calls. Code is available at https://github.com/EdWangLoDaSc/know2say.
MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models
Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs. When such a mismatch occurs, the CoT no longer faithfully reflects the actual reasons (i.e., decision-critical factors) driving the model's behavior, leading to the reduced CoT monitorability problem. However, a comprehensive and fully open-source benchmark for thoroughly evaluating CoT monitorability remains lacking. To address this gap, we propose MonitorBench, a systematic benchmark for evaluating CoT monitorability in LLMs. MonitorBench provides: (1) a diverse set of 1,514 test instances with carefully designed decision-critical factors across 19 tasks spanning 7 categories to characterize \textit{when} CoTs can be used to monitor the factors driving LLM behavior; and (2) two stress-test settings to quantify \textit{the extent to which} CoT monitorability can be degraded. Extensive experiments across multiple popular LLMs with varying capabilities show that CoT monitorability is higher when the decision-critical factors shape the intermediate reasoning process without merely influencing the final answer. More capable LLMs tend to exhibit lower monitorability. And all evaluated LLMs can intentionally reduce monitorability under stress-tests, with monitorability dropping by up to 30\% in some tasks that do not require structural reasoning over the decision-critical factors. Overall, MonitorBench provides a basis for further research on evaluating future LLMs, studying advanced stress-test monitorability techniques, and developing new monitoring approaches. The code is available at https://github.com/ASTRAL-Group/MonitorBench.