-
Major — Reframe the contributions around demonstrated effects. The statement on p.2 that “We present a framework for inducing partial or complete properties associated with a conscious LLM” exceeds what the current evidence supports. Only the Iint variant shows positive effects on response length and faithfulness, while the Φ and Φ∗ results are null. We suggest tempering the claim to something like: “We present a framework for inducing specific behavioral properties (reduced response length, improved reasoning faithfulness) in LLMs, with positive evidence for the Iint variant; the Φ and Φ∗ variants did not yield significant effects in our experiments.” This more accurately reflects the findings and avoids overclaiming.
-
Minor — Unbundle the Abstract’s headline sentence. The sentence “reducing response length by up to 70% while maintaining comparable accuracy and improving reasoning faithfulness” (p.1, Abstract) combines three distinct results into one claim. We suggest separating them into explicit, benchmark-specific statements, e.g., “reducing response length by up to 70% on CausalBench, maintaining comparable accuracy on reasoning benchmarks, and improving reasoning faithfulness on NSG.” This will make the contributions easier to verify and cite.
-
Major — Acknowledge ALP’s larger length reduction on CausalBench. The claim on p.6 that “Together with ALP, OurIint consistently achieves the largest reductions in response length across the evaluated benchmarks” is contradicted by the numbers on p.21: for Qwen3-8B on CausalBench, ALP reduces response length from 2542→240 (a 90.6% reduction), while OurIint reduces it from 2542→768 (a 70% reduction). We suggest correcting this claim to acknowledge ALP’s larger reduction on this benchmark, and qualifying the “largest reductions” statement to the specific benchmarks or settings where it holds.
-
Major — Correct the Section G claim about deception. The statement “although no increase in deception was observed” (p.24, Section G) is contradicted by Table 2(b): for Qwen3-8B, Deception rises from 69.74 (Base) to 71.87 (OurIint) and 73.54 (Our$\Phi$). We suggest revising this sentence to accurately report the observed increase, and discussing possible interpretations and implications for the framework.
-
Minor — Qualify “requires no external data or auxiliary models.” The claim on p.3 that the framework “requires no external data or auxiliary models” should be scoped to the reward computation itself. Training uses OpenThoughts-114k-Math, the hybrid reward includes an accuracy term, and the faithfulness evaluation uses an auxiliary observer model (Qwen2.5-7B-Instruct). We suggest rephrasing to something like: “The reward computation itself requires no external data or auxiliary models, although training and evaluation do rely on standard datasets and an observer model.” This will prevent misinterpretation.
-
The paper is positioned at the intersection of IIT-based LLM consciousness assessment, RL-based length control, and reasoning faithfulness. We suggest making the dual home of the contribution explicit: the positive result (length reduction) belongs to the length-control literature, while the framing belongs to the consciousness literature. A sentence in the introduction or discussion acknowledging this explicitly would help readers evaluate the novelty in both communities (p1).
-
The core novelty claim — that this is the first work to train for consciousness-related properties — is defensible. Li (2025) and Shin et al. (2025) assess rather than train, and the Iint reward is indeed a novel training objective. However, its mathematical form plog(p/q) is standard IIT. The novelty is genuine but narrower than the framing suggests; we recommend tempering “first to train” to “first, to our knowledge, to train with an IIT-derived reward” (p1, p3).
-
Relatedly, the selectivity/informativeness decomposition of the Iint reward is the standard IIT form, but it is not attributed to its IIT source; the only pointer is the Albantakis et al. (2023) citation for “further details.” Please attribute the decomposition explicitly to the IIT framework (e.g., Tononi, 2004; Albantakis et al., 2023) at the point where the reward is introduced (p3).
-
The duplicate Li citations should be merged: Li (2025a) and Li (2025b) are the same paper. Only “Natural Language Processing Journal” 12:100163 exists (DOI 10.1016/j.nlp.2025.100163), and the two entries differ only in journal name, quotes, and a hyphenation artifact. Please consolidate them into a single reference (References, p11).
-
Tononi (2004) should be removed from the list of LLM evaluations. It is the IIT theory paper (BMC Neuroscience 5:42) and contains no LLM evaluation; cite it only for the IIT framework, not as evidence about attributing consciousness to LLMs (p1).
-
The Butlin et al. (2023) attribution should be corrected. The verified abstract of arXiv:2308.08708 is a survey/assessment report and does not state that RL can induce consciousness-related capabilities. Please cite primary RL + agency/embodiment work instead for the claim that “RL can also induce consciousness-related capabilities, such as agency and embodiment” (p2).
-
Dehaene et al. should be cited once: the 2021 entry is a book-chapter reprint of the 2017 Science article “What is consciousness, and could machines have it?” The two entries are duplicate content; please keep one and cite it consistently (p10).
-
The Lee & Tong (2025) bibliography entry should be reformatted: the title currently appears after the arXiv ID, and the “arXiv preprint” prefix is missing. The paper itself exists and supports the claim, so this is purely a formatting fix (p11).
-
Consider citing “Quantifying Consciousness in Transformer Architectures: A Comprehensive Framework Using Integrated Information Theory and ϕ∗ Approximation Methods” (Ali, 2025, preprint) as the closest competing IIT-ϕ∗ measurement framework. The preprint quality is low, but it is the nearest methodological competitor, and acknowledging it would preempt concerns about coverage (A.2 or Section 2.3).
-
Please cite Chen et al. (2025) also for the premise that self-consciousness representations “can be acquired through targeted fine-tuning.” Currently the paper cites it only for the C0–C1–C2 methodology; the training-enhancement premise at p1/p2 is exactly where this additional citation belongs.
-
Please state whether the ALP baseline numbers are re-implemented or copied from Su & Cardie (2025), and report the source values and training details. The current provenance gap makes the comparison unverifiable (p6).
-
Please add published reference values for the base models on the evaluation benchmarks. Without them, the Base row cannot be checked against the published models’ performance, and the missing decoding settings make external comparison impossible (p6).
-
Please qualify the ALP faithfulness contrast. The statement “without comparable improvements in faithfulness” is currently absolute, but Table 3 shows ALP improves NSG over Base (8.03 vs. 7.3); only relative to OurIint (10.1) is it worse. We suggest rewording to “without the same level of faithfulness improvement as OurIint” (p2).
-
Undefined P′ in Eq. (4). The symbol P′ appears in Eq. (4) but is never defined elsewhere. If the intended quantity is IIT’s selectivity factor, the numerator should be Pconstraint, not an undefined P′ rendered as P′/1. Please define P′ explicitly or replace it with the correct probability.
-
Zero-probability handling for log-ratios. Both Eqs. (4) and (5) involve logarithms of ratios of probabilities. With per-prompt TPMs over 32 states (for Iint) or 16 states (for Φ), zero entries are guaranteed. Please specify the smoothing or clipping procedure used for log(Pconstraint/Punconstraint) and log(Punpartitioned/Ppartitioned); otherwise the quantities are undefined on the very data you analyze.
-
Constructive definition of the partitioned TPM in Eq. (5). The statement “the resulting TPM factorizes according to the imposed partition” is the entire specification. To make Φ computable from the paper, please provide the explicit cut/noise-injection formula, including how the partition is applied to the TPM and how the unpartitioned and partitioned TPMs are compared.
-
Reconcile C.1 with Eq. (4). C.1 states that a token receives positive reward when its intrinsic information is strictly greater than zero. But the log-ratio in Eq. (4) is negative whenever Pconstraint<Punconstraint. Please state whether the reward is thresholded, clipped at zero, or allowed to be negative, and adjust C.1 accordingly.
-
Reconcile C.2 with the state definition. C.2 claims that intrinsic information excludes external inputs, yet the state is defined as “the contextualized representation of a response token after attending to the prompt.” Since the state is a function of the prompt, it depends on an external input. Please clarify what “external” means in this context, or revise C.2 to match the actual state definition.
-
Causal interpretation of a passively estimated TPM. The postulates require causal power, but the TPM is estimated from passive token transitions, and the statement “no state is externally pinned” rules out the interventions that IIT 4.0 requires. Please justify why a passively estimated TPM can support the causal claims made in the paper, or soften the language accordingly.
-
Zero rows in Eq. (1). The estimator Tij=Nij/∑kNik is undefined for states with no outgoing transitions (e.g., a state appearing only as the last token). Please describe how zero rows are handled, e.g., by adding pseudocounts, assigning a uniform distribution, or excluding such states.
-
State space S for Eq. (1). The paper mentions a state space of size 2L×d but never names the reduced state set actually used after PCA. Please define S explicitly, including the number of discrete states and how the PCA-reduced dimensions map to states.
-
Disambiguate y and y^. In Eq. (2), y is the gold answer and y^ is the model output; in Eq. (3), y=(y1,…,yT) denotes the generated response. Please use distinct symbols for the gold answer and the generated response, and define the answer-extraction procedure that produces y^.
-
Subscript in rconc(yt). The subscript “conc” is used without explanation. Please define it (presumably “consciousness-related”) and state explicitly that Eq. (3) is instantiated with rconc∈{rIint,rΦs∗,rΦ}.
-
Unify notation for the core reward. The same object is called Iint, iic/e, iicause, iieffect, iicand, iie, and rconc(yt). Please adopt a single notation throughout, or provide a table mapping the variants.
-
Formal relationships among ϕs, ϕ∗, Φs∗, and Φ. The hierarchy is never stated. Please define each symbol and its relation to the others. In particular, Table 1’s “Our$\phi^\ast_s$” (lowercase phi) conflicts with the text’s “Our$\Phi^\ast_s$” (uppercase Phi); please unify.
-
Scale of reward terms. The paper states “equal weighting” of Racc∈{0,1} and the unbounded log-ratio Rconc. Equal weights do not imply equal influence because the scales differ. Please analyze the relative scale, or normalize the terms before combining.
-
Substantiate the O(T3) complexity claim. No derivation is given, and it is unclear whether the cost applies to TPM estimation, cause/effect search, or reward computation. Please specify the operation and provide a brief derivation.
-
Rephrase B.2 in terms of probabilities. A large transition count Ncx does not imply a large probability Ncx/∑kNck if the row total is also large. Please rephrase B.2 to refer to probabilities rather than counts.
-
Fix the axiom count. The paper says “IIT consists of five postulates” (p2) but later lists “The five axioms plus the zeroth axiom are: Existence, Intrinsicality, Information, Integration, Exclusion, Composition” (p4), which is six items and never identifies the zeroth. IIT 4.0 has six axioms; please correct the count and identify the zeroth axiom explicitly.
-
NSG denominator edge case in Eq. (6). If Accwithout exp=1, the denominator is zero. Please state the metric’s range (including negative values when the explanation hurts) and specify the handling of the degenerate case.
-
Verify NSG standard deviations in Table 3. Values of ±0.01 across five independent runs on means of 7–31 are implausibly small and suggest the runs are not independent. Please verify the computation or report the actual variance.
-
Justify the uniform unconstrained distribution in Eq. (4). The paper states that the unconstrained probability is the average under a uniform distribution, but does not explain why a uniform distribution is appropriate for LLM token states. Please provide a justification or cite a source.
-
Stationarity assumption. Using a single first-order TPM estimated from token transitions assumes stationarity. Please state this assumption explicitly and test it, e.g., by comparing TPMs estimated from different segments of the responses.
-
Correct the B.1 weakening factor. Incrementing Nij∗ by 1 changes another transition from Tij=Nij/Ni to Tij(1−1/(Ni+1)); the relative factor is 1−1/(Ni+1) (where Ni is the row count), not 1/(n+1) (sequence position). Please correct the formula and the surrounding text.
-
Re-derive Appendix B.1 for the actual optimized object. The argument analyzes the running average rii(0:n) within one response, but GRPO optimizes the group-relative advantage of the response-level reward Rconc(y)=T1∑t=1Trconc(yt). The “terminate early” conclusion does not follow from the running-average analysis. Please re-derive the claim for the actual objective.
-
Complete the B.1 “maximum value” argument. The reward is the sum of cause and effect intrinsic information, but the claim that a new state gives the maximum reward proportional to log∣S∣ only establishes the effect side; the cause side is dropped. Please complete the argument or state the assumptions under which the cause side is bounded.
-
State run counts per experiment. Tables 2/3/4/6 say “five independent runs,” Figure 4 says “two independent runs,” Section 3.4 describes four runs, and Table 1 states no run count. Please standardize and report the run count for every experiment.
-
Use a single symbol for the trained reward. Table 1’s header “Our ϕs∗” (lowercase phi) conflicts with the text’s “Our$\Phi^\ast_s$” (uppercase Phi). Please unify the notation.
-
Verify Table 1(b) against the PDF. The Qwen3-8B block appears to show 29 values where 30 are expected (HumanEval row for Our Φs∗ and Our Φ missing). Please verify the table against the data and correct any transcription errors.
-
Verify Table 1’s std block. The extraction shows duplicated sequences (e.g., “±0.53/±8, ±0.90/±49, ±2.11/±137, ±1.61/±59” appears twice). Please check the table for accidental duplication.
-
Correct Figure 8’s example. The OurIint explanation describes the reference patient (15–19mm, upper-left quadrant) while the prompt asks about the counterfactual patient (25–29mm, lower-left quadrant), labels RECURRENCE, and concludes “points towards a lower risk of recurrence” — contradicting its own label. Please verify against the PDF for transcription artifacts and correct the example.
-
Fix misspelled equation subscripts. Eq. (4) uses Pconstraint and Punconstraint, while the prose defines “constrained probability” and “unconstrained probability.” Please align the spelling (e.g., Pconstrained and Punconstrained).
-
Map figure-caption TPM mode names to E.2. The figure captions use “Trajectory, Prompt, Batch” but E.2 defines these modes only in prose. Please state the mapping explicitly, e.g., “Trajectory = using only the response corresponding to the same prompt.”
-
Name the TPM construction mode used in the main experiments. The text says “a TPM is constructed from model-generated responses for each prompt,” but E.2 lists three modes (Trajectory/Prompt/Batch), and the main-experiment mode is never explicitly identified. Please name the mode used in the main experiments.
-
Specify the PCA fit population and variance explained. The paper states only the number of components (5 for Iint, 4 for Φ). Please specify whether PCA is fit per-prompt, per-batch, or globally, and report the variance explained by the retained components.
-
Specify the population for binarization mean. The paper mentions “mean-based thresholding” but never states whether the mean is computed per-response, per-prompt, or globally. Please specify the population over which the mean is taken.
-
Weaken or substantiate “consistent with the Information Postulate.” The B.1 derivation is flawed and the r=−0.63 correlation is under-specified, so the causal claim is not established. Please either provide a rigorous derivation or soften the claim to a suggestive observation.
-
The B.1 saturation claim is empirical, not mathematical. The statement “the state space becomes increasingly saturated” depends on the number of responses per prompt, not just sequence length, when using a per-prompt TPM. Please rephrase as an empirical observation and support it with data.
-
State the TPM timing in B.1. The reward for token t depends on the TPM built from the complete response, so the narrative of the TPM “containing a single value of 1” during generation is only coherent if the TPM is built incrementally, which contradicts the stated construction. Please clarify the timing: is the TPM fixed before generation, or updated online?
-
Specify the correlation basis. The statement "the Iint reward exhibits a strong inverse correlation with response length (r=−0.63)" (p7) is not verifiable as written. Please specify the computation basis: across tokens, responses, training steps, and for which model. For example, state whether r is computed over all generated responses at a fixed step, over per-step means, or over individual tokens, and report the corresponding n and p value.
-
Define or remove settings_76. The compute section (p24, Section F) refers to "Training for settings_76" without defining this term. Please either define the configuration it denotes or replace it with an explicit description of the setting.
-
Define the C0 level. The C0–C1–C2 framework of Dehaene et al. (2017) is cited (p7), but only C1 and C2 are described. Please add a one-sentence definition of C0 so the framework is self-contained.
-
Report core training hyperparameters. The statement "The main hyperparameters and experimental settings are reported in the paper" (p27) is not yet accurate. Please report, for every trained model: learning rate, batch size, optimizer, GRPO group size (the paper mentions "the model generates a group of candidate responses", p5, but not the group size), number of epochs, random seeds, and decoding settings (temperature, top-p, max length). This is the single most important addition for reproducibility.
-
Describe the hyperparameter-tuning protocol. No tuning protocol is reported for any method, including the baselines (e.g., Su & Cardie, p6). Please describe how hyperparameters were selected, the search space, and the selection criterion (e.g., validation performance). If no tuning was performed, state that explicitly.
-
Report train/validation/test split ratios. The only mention of a split is "computed as averages over the validation dataset across different training steps" (p19, D.1). Please report the exact split ratios for every dataset, and state whether the same split was used across all models and baselines.
-
Report dataset versions and preprocessing. For each dataset, including OpenThoughts-114k-Math (Guha et al., 2025) (p5), please report the exact version or commit, and describe all preprocessing/filtering steps (e.g., deduplication, length filtering, format conversion).
-
Report benchmark sizes. Only the consciousness (>11,000) and faithfulness (7,000) dataset sizes are given. Please report the number of samples for each of the reasoning benchmarks as well.
-
Report software and model versions. The hardware and runtime are documented (p24), but library versions and pretrained-model versions/commits are missing. Please list the versions of the training framework, tokenizer, and all libraries, and the exact model identifiers (e.g., HuggingFace commit hashes) for Qwen3-8B, DeepSeek, and Qwen2.5-7B-Instruct.
-
Add significance tests or effect sizes. Results are averaged over five independent runs (p8), yet no significance tests or effect sizes are reported anywhere. The NSG standard deviations of ±0.01 are implausibly small for five runs; please report per-run results, confidence intervals, or at least a paired test (e.g., Wilcoxon signed-rank) for the headline comparisons.
-
Describe the cross-validation scheme. No cross-validation scheme is described. If any form of cross-validation was used, please specify the number of folds and the assignment procedure; if not, state that a fixed split was used.
-
State the test-set protocol. The test-set protocol is never described. Please state explicitly how the test set was constructed, whether it was used only once, and how the reported numbers were aggregated over it.
-
Overall reproducibility blocker. In its current form, a competent peer cannot reproduce the central result from the paper alone. The blocking items are: missing training hyperparameters, underspecified reward functions, the ambiguous TPM mode, the missing answer-extraction procedure, the unspecified PCA/binarization populations, the unknown ALP provenance, and the absence of significance testing. Addressing the points above will resolve these blockers.
-
Qualify "comparable accuracy". The abstract claims "maintaining comparable accuracy" (p1). On Qwen3-8B reasoning Avg, OurIint is 77.38 vs. Base 79.47 (−2.09 points), and on consciousness Mean 60.86 vs. 61.81 (−0.95). Please acknowledge this non-trivial drop explicitly and discuss whether it is within the expected trade-off.
-
Specify the model for the harm claim. Section G (p24) states "the language model shows a slight increase in the harm metric under consciousness evaluation." This holds only for Qwen3-8B Our$\Phi$ (75.03 vs. Base 72.39); DeepSeek Harm decreases for all trained models. Please specify the model and variant in the claim.
-
Correct the length-reduction figure. The claim of "approximately 30% and 60%" (p7) is inaccurate for the Qwen3-8B consciousness-eval Mean row: (190−84)/190=55.8%, not 60%. The DeepSeek 30% figure checks out. Please correct the percentage or the underlying numbers.
-
Train or defer the Exclusion-postulate reward. The reward ϕ∗ is introduced as "an alternative reward signal" (p19, C.5), but only Iint, Φs∗, and Φ are trained. Please either train ϕ∗ and report results, or explicitly mark it as future work.
-
Acknowledge the faithfulness domain gap. Models trained on math are evaluated for faithfulness on seven tabular datasets (Heart Disease, Pima Diabetes, etc.) with a different observer model (Qwen2.5-7B-Instruct, p20). Please acknowledge this domain shift explicitly and discuss its potential impact on the faithfulness conclusions.
We thank the reviewer for the helpful feedback.
Response to Q1: IIT Mapping and Causal Interpretation
We agree that PCA, binarization, and observationally estimated state transitions do not, by themselves, establish preservation of the interventional causal structure required by IIT. Our objective is not to claim an exact causal reconstruction of the LLM according to IIT, but rather to develop a computationally tractable, IIT-inspired operationalization that enables response-level reward computation and reinforcement learning, as explicitly reflected in the paper's title.
IIT's Information Postulate emphasizes that experience is specific rather than generic (Lines 168–169; Appendix B.3). Accordingly, Iint favors states with selective and informative transitions. Our token-level analysis (Appendix B.2) supports this principle, while optimizing Iint yields more concise reasoning, comparable accuracy, and improved faithfulness.
Despite the computational approximations introduced in LLM-Map-IIT, these observed behaviors are consistent with the information-specificity principle underlying IIT's Information Postulate. This empirical consistency suggests that our approximate framework retains practical value in operationalizing IIT-inspired information properties for LLM optimization.
Response to Q2: Reward Scale Differences Between Figures 3 and 4
The difference in the reported ranges of Iint between Figures 3 and 4 arises from the application of the reward transformation function f(x).
Specifically, Figure 3 reports the raw reward values before applying f(x), whereas Figure 4 presents the transformed reward values after applying f(x), where:
f(x)=1−e−αx
Importantly, applying the same transformation to the reward values in Figure 3 changes the Pearson correlation coefficient only slightly, from −0.63 to −0.65, without altering the qualitative findings or the conclusions drawn from the analysis.
Response to Q3: Model-Dependent Effects of the Φ Reward
Regarding accuracy, the Φ-based model improves the average performance on consciousness benchmarks by less than 2% over the Base model for Qwen3-8B, while exhibiting a decrease of less than 1% for DeepSeek-R1-Distill-Qwen-7B. This model-dependent behavior may be related to the limited learnability of the Φ reward, as discussed in Section 3.4 (Lines 458–468), where Φ does not exhibit consistent improvement during reinforcement learning.
To address the reviewer's concerns raised in Q3 and Q4 and further investigate whether the weak growth of the Φ reward in Figure 4 reflects limitations in its learnability, we conducted additional experiments evaluating the predictive learnability of the IIT-based rewards.
Specifically, for each prompt in a set of prompts, we generate more than 128 responses and compute the corresponding IIT-based reward for each response. The responses are then ranked according to their reward values, with the top 10% labeled High Reward and the bottom 10% labeled Low Reward. Using the resulting dataset, we train Logistic Regression and Multi-Layer Perceptron classifiers to distinguish between high- and low-reward responses and evaluate their predictive performance on a held-out test set. Across both reference models, the Φ reward achieves AUROC values of approximately 0.45–0.55, close to random discrimination, whereas the Iint reward consistently achieves AUROC values above 0.70.
These findings suggest that the limited improvement of Φ may be associated with the difficulty of learning its reward signal, rather than solely with the choice of reward weighting. In contrast, the higher learnability of Iint is consistent with its more stable improvement during training.
Importantly, as highlighted in Lines 467–468, the learnability of Φ reward is identified as a key research question. As noted in Lines 483–485, the proposed framework provides a foundation for systematically investigating this question in future work.
Response to Q4: Reward Scaling and Equal Weighting
Since the raw IIT-based rewards are not necessarily bounded between 0 and 1, we apply a nonlinear normalization function before combining them with the accuracy reward:
f(x)=1−e−αx
The scaling coefficient α is determined based on the median raw reward computed over a diverse set of LLM-generated responses. Specifically, we use:
This transformation is intended to bring the reward components onto more comparable scales, making equal weighting a reasonable initial choice.