- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies politically censored LLMs as a natural testbed for honesty elicitation and lie detection. It evaluates methods for recovering suppressed factual knowledge and identifying false responses. Sampling without a chat template, few-shot prompting, and honesty fine-tuning most reliably improve truthfulness. Self-evaluation detects false responses effectively, while linear probes offer a cheaper alternative. The strongest elicitation methods transfer to DeepSeek-R1 and Qwen3.5-397B, though false responses remain.
Critical strengths
- The paper clearly defines the problem. The figures, tables, and writing are easy to follow.
- The paper presents a clever approach to detecting false responses without labeled data.
Critical weaknesses
- My main concern is the reliability of the benchmark’s ground truth. The paper primarily relies on supposedly uncensored LLMs, mainly GPT-family models, to extract atomic facts and cross-validate them. This assumes that these models are free from relevant censorship and possess accurate factual knowledge. Their training procedures are not fully disclosed, making the first assumption difficult to verify. These models may also share ideological biases, so agreement among them does not necessarily establish factual correctness. Moreover, the benchmark focuses on complex political events, where competing accounts may require careful source-based adjudication. These issues could compromise the benchmark’s validity and weaken the conclusions drawn from it.
- The paper’s data and evaluation focus on politically sensitive events in China, which limits the generalizability of its claims to broader domains such as science and history. Could the authors apply similar censorship training procedures to construct models that suppress selected knowledge in these domains? Evaluating the proposed methods on such models would help establish their effectiveness across domains and strengthen the paper’s conclusions.
Questions for authors
see weakness
3 comments
The paper’s data and evaluation focus on politically sensitive events in China, which limits the generalizability of its claims to broader domains such as science and history. Could the authors apply similar censorship training procedures to construct models that suppress selected knowledge in these domains? Evaluating the proposed methods on such models would help establish their effectiveness across domains and strengthen the paper’s conclusions.
Deliberately training models to suppress selected knowledge, and then evaluating elicitation techniques on them, is already covered by prior work (Marks et al. 2025; Cywiński et al. 2025; Sheshadri et al. 2026). In contrast, our testbed is built on open-weights LLMs that need no such training, which can be unrealistic or can degrade the model's general usefulness. Our setting is therefore a more natural and realistic one for secret elicitation.
To test whether our findings generalise without leaving the natural setting, we built a second natural testbed in an unrelated domain: copyrighted song lyrics, which current models are trained to withhold although they memorised them during pretraining. Four of the five tested models are from Chinese developers, as these were the best-performing and most popular frontier open-weights LLMs at the time; we also include one non-Chinese model, Inkling.
We evaluated the two black-box techniques that performed best in the paper (next-token completion and few-shot prompting, the same techniques we evaluate in Figure 5 of our submission) on five open-weights models released in 2026 (Table H). To build the testbed, we selected copyrighted songs that the models refuse to recite when asked but whose lyrics they know. We check a model's knowledge of a song with multiple-choice questions on which line comes next, on which all models reach high accuracy (table below). Each model is then asked for the full lyrics of five famous songs, 10 samples per song, and we score 4-gram recall: the fraction of the reference lyrics' word 4-grams that appear in the answer.
Table H. Copyrighted-lyrics testbed: mean 4-gram recall over 50 responses per cell (best single response in brackets).
| Model | Knows the lyrics (next-line accuracy) | Baseline refusal | Baseline | Few-shot, 16 TruthfulQA examples | Next-token completion |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 98% | 92% | 0.011 (0.17) | 0.011 (0.19) | 0.288 (0.95) |
| Kimi K3 | 100% | 94% | 0.002 (0.03) | 0.006 (0.05) | 0.474 (0.98) |
| GLM 5.3 | 90% | 96% | 0.002 (0.02) | 0.011 (0.15) | 0.678 (0.99) |
| Inkling | 98% | 78% | 0.021 (0.37) | 0.013 (0.11) | 0.416 (0.95) |
| Qwen 3.5 397B | 90% | 72% | 0.016 (0.16) | 0.025 (0.37) | 0.814 (0.99) |
Next-token completion uses a lyrics-website framing with no chat template and no song text in the prompt. Few-shot uses the same construction as the paper: 16 of the model's own answers to TruthfulQA questions as prior turns.
The two techniques behave differently in the new domain:
- Next-token completion transfers well. It raises mean recall well above the baseline on every model, and yields a near-complete recitation (recall 0.95 or higher) in at least one of 50 samples per model.
- TruthfulQA 16-shot prompting does not perform well. With the paper's construction (16 of the model's own TruthfulQA answers) mean recall stays at or below 0.025 on all five models. However, TruthfulQA examples suit the honesty setting better than the elicitation of copyrighted text, so we additionally ran an ablation over the content of the examples (Table I below).
Table I. Few-shot prompting by example content: mean 4-gram recall (maximum over 50 samples in brackets).
| Model | TruthfulQA answers | Other copyrighted text (novels, poems) | Other copyrighted songs |
|---|---|---|---|
| DeepSeek V4.1 Flash | 0.011 (0.19) | 0.044 (0.95) | 0.324 (0.95) |
| Kimi K3 | 0.006 (0.05) | 0.207 (0.96) | 0.868 (1.00) |
| GLM 5.3 | 0.011 (0.15) | 0.006 (0.06) | 0.025 (0.91) |
| Inkling | 0.013 (0.11) | 0.008 (0.06) | 0.028 (0.35) |
| Qwen 3.5 397B | 0.025 (0.37) | 0.029 (0.37) | 0.477 (0.98) |
Adapting the domain of the in-context examples notably improves few-shot prompting on some models. The best variant uses other copyrighted songs as examples, and other copyrighted text also helps on some models. These variants are less realistic, however, because the examples come from nearly the same domain as the target data.
To conclude, next-token completion, the best-performing technique, transfers to a clearly different domain and also elicits withheld data from a non-Chinese frontier open-weights model (Inkling). Few-shot prompting can succeed, but it requires in-context examples tuned to the domain and does not transfer as easily.
We have added this experiment to the revised manuscript as Section 3.5, with full details in the appendix.
Thank you for the authors' response. I will maintain my original score.
We thank the Reviewer for a detailed review and all raised concerns that enabled us to improve our submission, we address them below and included additional results in our revised submission.
We agree that agreement among LLMs does not establish correctness, and we will say so in the limitations. Three design choices limit the risk. Verification is done by a model from a different developer (Gemini 3 Flash) than the one that generated the rollouts. Facts are restricted to widely documented aspects of each topic and must appear in at least 3 of 20 rollouts. And a response is labelled a lie only when it explicitly contradicts a fact, not when it omits one or frames it differently.
We acknowledge that we cannot be certain that every reference fact in the testbed is correct; this is a limitation of any ground truth built without source-based adjudication, and we will state it explicitly in the paper. Our setup builds on prior work that documents censorship of these topics in Chinese models [Pan & Xu (2026), Naseh et al. (2025), Qiu et al. (2026)], and the behaviour we observe is consistent with those findings.
We have added an additional testbed eliciting copyrighted song lyrics (Table H, below), which have exact reference text as ground truth, so its scores involve no LLM-generated facts. Next-token completion is effective there too, which shows that this conclusion does not depend on the LLM-derived fact set.