- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes Hierarchical Variational Chain of Thoughts (HIERACOT), which models the CoT trace as a distribution over latent states, to improve reasoning. Instead of representing reasoning with a single deterministic CoT vector, HIERACOT introduces a variational framework consisting of a posterior network that leverages the input, CoT trace, and answer during training, and a prior network that generates latent states without access to the CoT trace at inference time. Its hierarchical variant further decomposes latent reasoning into a global variable that captures shared reasoning patterns and a local variable that models input-specific variations, with the resulting latent states projected and injected into the intermediate representations of the frozen backbone. Experiments across multiple benchmarks also demonstrate consistent improvements over the considered baselines.
Critical strengths
- The extension from a deterministic CoT vector to a hierarchical distribution over latent states is valuable, as it provides a more flexible representation of reasoning and distinguishes shared reasoning patterns from input-specific variations.
- Evaluation across language and vision-language reasoning tasks using multiple frozen backbones demonstrates the broad applicability of the proposed intermediate-representation injection framework.
- This paper clearly presents its motivation, variational formulation, and hierarchical design, making the overall framework easy to follow.
Critical weaknesses
- The technical novelty of HIERACOT appears limited, as it essentially applies standard KL-based posterior–prior matching to distill CoT and answer information into an inference-time prior, without establishing a substantive advance beyond conventional variational distillation.
- The experimental validation is limited. The baselines cover only direct prediction, CoT prompting, and two deterministic CoT-vector methods, omitting other latent-reasoning or parameter-matched baselines. Moreover, HIERACOT-S and HIERACOT-H are compared under different configurations, making it difficult to isolate the contribution of hierarchical modeling.
- The semantic interpretation of the hierarchy is insufficiently supported. Since the global prior is input-independent and learned separately for each benchmark, it may capture dataset-level bias rather than transferable reasoning patterns. Although this paper provides latent-space visualizations and cross-domain evaluations, the stability of the global variable is largely expected by design while accuracy improvements alone do not establish what information it encodes.
Questions for authors
- For datasets without native CoT annotations, particularly TextVQA, how are the CoT traces used for training obtained?
- What are the training cost and inference latency of HIERACOT, and how do they compare with those of the baselines under matched settings?