- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper investigates the “expression gap” between uncertainty signals encoded in language models’ hidden states and those expressed in their responses. Across four model families, linear probes detect uncertainty, unsupportedness, and contradictions that are not consistently reflected in generated answers. The authors propose a probe-gated logit-bias intervention to encourage uncertainty expression and compare it with prompting and activation steering. A blinded semantic evaluation confirms improvements on two model families, while revealing that an apparent improvement on another primarily reflects wording changes. The results highlight model-dependent gaps between internal representations and output behavior, as well as the importance of semantic evaluation.
Critical strengths
The paper addresses an important and widely studied problem concerning the gap between LLMs’ internal uncertainty signals and their expressed behavior. It presents a comprehensive experimental evaluation across multiple model families and tasks, supported by control experiments, intervention comparisons, and a blinded semantic audit.
Critical weaknesses
- The expression gap is overinterpreted. Defining the expression gap as overlooks the joint distribution of probe predictions and generated responses. This difference equals , rather than the proportion of inputs where the probe detects uncertainty but the response fails to express it, . The two disagreement types can cancel out. Reporting their joint distribution would better support the “knows but does not say” interpretation.
- Practical applicability and probe validity remain insufficiently established. Experiments are restricted to 7–8B models, and probes require separate training for each model and task, leaving their applicability to frontier-scale models unclear. The evidence also does not establish whether a linear probe at layer 17’s last-input-token position adequately captures epistemic state, or how it compares with alternative layers, token positions, and probe architectures.
- Coverage and comparison of relevant methods are incomplete. Particularly relevant omissions include INSIDE (ICLR 2024), LLM-Check (NeurIPS 2024), Lookback Lens (EMNLP 2024), and PRISM (ACL 2025). Discussing these approaches and comparing selected methods under matched information and computational budgets would clarify the paper’s incremental contribution.
Questions for authors
- Figures 2 and 3 primarily emphasize differences across relatively small, older models. What broader conclusions are these comparisons intended to support, and what insights do they offer for understanding or improving frontier-scale LLMs?
- What do the authors consider the paper’s central novel contribution: the internal probe, the comparative analysis across models, or the intervention method? The novelty and supporting experimental evidence for each component appear limited. Could the authors clarify the principal advance over prior work and provide evidence that more directly establishes it?