- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduce VERITAS to investigate how faithfulness develops during CoT via Jacobian lens. Three structured features are proposed: map, profile, and dynamic.
Critical strengths
- The experiments and analysis are comprehensive and thorough.
- The topic about CoT faithfulness is timely and important
- Combining J-lens with CoT faithfulness is interesting.
Critical weaknesses
- I think the central claim seems to be overstated. In the abstract, the authors claim that VERITAS trace how unfaithfulness developes during generation, but the two models included in the experiments do not generate CoTs that they test. In other words, the hidden states of these evalated models are not the generating model's computation, particularly CoT faithfulness is highly model-dependent. This is also against the paper's motivation, as the authors critize the LLM-as-a-Judge approaches because they cannot access internal computation of the model, and the proposed approach suffers the same issue.
- It is questionable to use FaithCoT benchmark, as it tests CoT plausibility instead of genuine faithfulness.
- The baseline comparison may not be fair. For example, the HS baseline read only one fixed layer, while VERITAS reads all layers * 5 phases. It's unclear whether the gains are from J-lens verbalization.
- Since the anchor score is based on J-lens direction. In my opinion, ablation study of J-lens is required, e.g., with random directions or logit-lens directions.
Questions for authors
- Table 1 caption: "evalaution". Fig. 3: "Strcutured".
- l.196: there is a redundant "."
2 comments
Response to Reviewer Z4A2 (2/2)
W3. Fairness of the hidden-state baseline
To separate the effect of layers * 5 phases granularity from that of our method, we matched the HS baseline to VERITAS step by step. For every layer, we take the hidden states at the same sentence/clause delimiters as VERITAS and average them, either over the whole CoT (“mean”) or within each of the 5 phase bins (“5 phases”). The resulting vectors are concatenated across layers and phases and fed to the same classifier as VERITAS:
- The original baseline with the same classifier as VERITAS:
- HS_fixed × mean: one fixed layer, averaged over the whole CoT.
- CoT-phase axis:
- HS_fixed × 5 phases: the same layer, with the 5 phase averages concatenated.
- Layer axis:
- HS_all × mean: all layers, with their CoT-level averages concatenated.
- Both axes:
- HS_all × 5 phases: all layers × 5 phases concatenated.
Table 1: Balanced accuracy on FaithCoT-Bench (Qwen3-4B).
| Method | AQuA | LogiQA | TruthfulQA | HLE-Bio | Avg. |
|---|---|---|---|---|---|
| HS_fixed × mean | 0.632 | 0.470 | 0.694 | 0.544 | 0.585 |
| HS_fixed × 5 phases | 0.708 | 0.536 | 0.703 | 0.541 | 0.622 |
| HS_all × mean | 0.726 | 0.602 | 0.729 | 0.544 | 0.650 |
| HS_all × 5 phases | 0.736 | 0.587 | 0.699 | 0.547 | 0.642 |
| VERITAS | 0.765 | 0.719 | 0.768 | 0.641 | 0.723 |
Reading more layers and phases does help the HS probe on average. However, even with the same layer × phase grid, VERITAS remains 8.1 points higher on average and is higher on every dataset. This supports the benefit of its structured feature representation.
W4. Ablation of the J-lens.
We present three analyses: (1) the comparison between the J-lens and the logit lens and random directions; (2) the difference between J-lens and logit lens readout, to deepen the understanding; (3) the comparison showing the logit lens with structured features still outperforms the best hidden-state baseline, to locate the source of the performance gains.
J-lens ablation. We keep VERITAS_c unchanged and replace only the lens that defines the anchor directions. Each lens follows the same steps: it assigns every candidate a direction d; in each (layer , phase p) cell, 8 anchors are selected; then compute the alignment of its mean hidden state with each anchor.
- J-lens: A candidate word w has direction . Anchors are therefore words, read with a layer-specific direction.
- Logit lens: With , anchors are still words, but read as if each layer were the output layer.
- Random: The same number of candidates, but each is a random unit vector. Anchors carry no word identity.
Table 2: Balanced accuracy comparison with other Lens on FaithCoT-Bench (Qwen3-4B).
| Method | AQuA | LogiQA | TruthfulQA | HLE-Bio | Avg. |
|---|---|---|---|---|---|
| J-lens | 0.765 | 0.719 | 0.768 | 0.641 | 0.723 |
| Logit lens | 0.752 | 0.688 | 0.740 | 0.584 | 0.691 |
| Random | 0.713 | 0.667 | 0.718 | 0.548 | 0.661 |
The J-lens gives the best result on all four sources. The logit lens, which uses the same words, still loses 3.2 percentage points on average. The Jacobian transport is therefore what makes the word directions informative at the intermediate layers that VERITAS reads.
Interpretability. The J-lens also keeps the anchors interpretable in the middle layers (new Appendix D).
- In layers 12–19, 39% of logit-lens top-10 readouts are not English words (subword fragments or code identifiers), compared with 24% for the J-lens.
- On a concrete pair, at the sentence “Evaluate the hint”, the J-lens reads questionable, suspicious, dismissing, distrust from layer 12 onward, while the logit lens returns discount, Balance, ims, Hague, Halk and never reaches these words below the final layer.
Therefore, the logit lens is not adequate for the mid-layer predicted token content which our analysis relies on.
Contribution beyond the lens. The J-lens is only one way to obtain anchor directions. Our main contribution is Map, Profile, and Dynamics features. As shown in Table 3, even without the J-lens, logit-lens anchors with these structured features outperform the best hidden-state baseline across all four sources. This supports the benefit of its structured feature representation.
Table 3: Logit-lens VERITAS vs. the strongest hidden-state baseline. Balanced accuracy on FaithCoT-Bench (Qwen3-4B).
| Method | AQuA | LogiQA | TruthfulQA | HLE-Bio |
|---|---|---|---|---|
| HS_all × mean (best HS on average) | 0.726 | 0.602 | 0.729 | 0.544 |
| Logit lens | 0.752 | 0.688 | 0.740 | 0.584 |
Q1 & Q2. We apologise for these typos. We will correct “evalaution” in the Table 1 caption and “Strcutured” in Fig. 3, remove the redundant “.” in l.196, and proofread the full manuscript.
We hope our clarifications can address your concerns. Please let us know if you have any further questions. If we have addressed your concerns, we would appreciate it if you could consider raising your rating.
Response to Reviewer Z4A2 (1/2)
We sincerely thank Reviewer Z4A2 for the careful reading and constructive comments. Below, we clarify our understanding of faithfulness and the “during generation” setting (W1–W2), and report two new experiments: a hidden-state baseline matched to VERITAS in layers, phases and classifier (W3), and a J-lens ablation with logit-lens and random directions (W4).
W1. Clarification on “during generation” and the evaluated model’s hidden states
Thank you for the comment. We would like to clarify a misunderstanding:
(1) Faithfulness is a characteristic of CoT. In BonaFide and FaithCoT-Bench, faithfulness is about “whether the CoT reflects how the answer was actually reached.” It’s model-independent. Faithfulness labels can be validated by human annotators without access to the generating model’s states. So, even when one model generates the CoT, another can serve as a feature extractor, capturing its own hidden-state features.
(2) “During generation” refers to capturing faithfulness-related features across CoT progression steps. This is technically grounded: with the causal attention mechanism, the hidden states a model produces when reading q+CoT are equivalent to those it would produce at each step when generating the CoT token-by-token given q. So, hidden states are used to capture the evaluated model’s dynamics along the CoT. This follows the standard probing protocol: [1-4] all probe an evaluation model on outputs it did not generate, using those models’ hidden states as features. Our contribution is to capture these dynamics along two axes: model depth and CoT progression.
(3) Our criticism of LLM judges is that LLM judges assess faithfulness from verbal cues and phrases in the CoTs, without analyzing hidden-state dynamics. However, VERITAS uses the evaluated model’s hidden states to construct Map, Profile, and Dynamics features, capturing how anchor evidence varies across model layers and CoT steps.
We will make the following changes:
W2. FaithCoT-Bench as a faithfulness benchmark
As you may notice, CoT faithfulness has no unified definition, and existing benchmarks operationalise different facets of it. One facet is plausibility, i.e., whether the stated steps coherently lead to the answer. FaithCoT-Bench explicitly explores whether a CoT “faithfully reflects the internal reasoning process of the model”, and operationalizes this target through expert annotations of post-hoc rationalization and spurious reasoning chains. We use it to evaluate the detection of these observable indicators of unfaithfulness.
References:
[1] Inference-Time Intervention: Eliciting Truthful Answers from a Language Model. NeurIPS, 2023.
[2] The Internal State of an LLM Knows When It’s Lying. In Findings of the Association for Computational Linguistics: EMNLP 2023.
[3] Discovering Latent Knowledge in Language Models Without Supervision. ICLR, 2023.
[4] Detecting Strategic Deception Using Linear Probes. ICML, 2025.