Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention

• URL: http://arxiv.org/abs/2606.01243v1
• Date: Sun, 31 May 2026 13:52:24 GMT
• Title: Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention
• Abstract summary: This paper bridges the gap between mechanistic interpretability and actionable control.<n>We first present a systematic analysis using structural, causal, and geometric probes.<n>We then operationalize these interpretability insights into a suite of training-free, decode-time interventions.
• Score: 33.40772052822545
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Latent reasoning enables Large Language Models (LLMs) to perform multi-step inference within continuous hidden states, offering efficiency gains over explicit Chain-of-Thought (CoT). However, the opacity of these continuous thought vectors hinders their reliability and controllability. This paper bridges the gap between mechanistic interpretability and actionable control. We first present a systematic analysis using structural, causal, and geometric probes, revealing that latent vectors encode compressed, faithful representations of reasoning steps, with early vectors acting as critical causal hubs. Building on this, we operationalize these interpretability insights into a suite of training-free, decode-time interventions that refine the latent reasoning process by imposing the identified geometric and semantic priors. Extensive experiments across multiple model scales and diverse task domains demonstrate that our approaches consistently improve reasoning accuracy. Our interpretability-guided interventions consistently unlock latent capabilities and improve reasoning accuracy without any parameter updates.

Related papers

• Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models [46.26628756478016]
  Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data.<n>We show that reasoning conflicts are internally detectable, as confidence scores significantly drop during conflicting episodes.<n>Our findings establish that while LLM reasoning is anchored to concrete instances, active mechanistic interventions can effectively decouple logical schemata from data.
  arXiv  Detail & Related papers  (2026-04-29T22:55:40Z)
• How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision? [45.11635323173876]
  We conduct a comprehensive analysis of latent reasoning methods to better understand the role and behavior of latent representation in the process.<n>We find that while latent representations can encode multiple possibilities, the reasoning process does not faithfully implement structured search.<n>Our findings reveal a trade-off associated with supervision strength: stronger supervision mitigates shortcut behavior but restricts the ability of latent representations to maintain diverse hypotheses.
  arXiv  Detail & Related papers  (2026-02-25T22:00:59Z)
• Beyond Dense States: Elevating Sparse Transcoders to Active Operators for Latent Reasoning [25.054823575096332]
  We propose LSTR (Latent Sparse Transcoder Reasoning), a latent reasoning framework that elevates sparse transcoders into active reasoning operators.<n>At its core, LSTR employs a Latent Transition Transcoder (LTT) with a residual skip architecture that decouples linear manifold transport from sparse semantic updates.<n>Extensive experiments show that LSTR preserves reasoning accuracy and compression efficiency while substantially improving interpretability.
  arXiv  Detail & Related papers  (2026-02-02T06:08:35Z)
• From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models [77.04403907729738]
  This survey charts the evolution of uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.<n>We demonstrate how uncertainty is leveraged as an active control signal across three frontiers.<n>This survey argues that mastering the new trend of uncertainty is essential for building the next generation of scalable, reliable, and trustworthy AI.
  arXiv  Detail & Related papers  (2026-01-22T06:21:31Z)
• Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts [74.47786985522762]
  We identify a critical failure mode termed textual inertia, where models tend to blindly adhere to the erroneous text while neglecting conflicting visual evidence.<n>We propose the LogicGraph Perturbation Protocol that structurally injects perturbations into the reasoning chains of diverse LMMs.<n>Results reveal that models successfully self-correct in less than 10% of cases and predominantly succumb to blind textual error propagation.
  arXiv  Detail & Related papers  (2026-01-07T16:39:34Z)
• SpiralThinker: Latent Reasoning through an Iterative Process with Text-Latent Interleaving [4.732347368043908]
  SpiralThinker is a unified framework that performs iterative updates over latent representations.<n>A progressive alignment objective combined with structured annotations maintains coherence between latent and textual reasoning.
  arXiv  Detail & Related papers  (2025-11-12T05:05:42Z)
• Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought [64.43689151961054]
  We theoretically analyze the training dynamics of a simplified two-layer transformer on the directed graph reachability problem.<n>Our analysis reveals that during training using continuous thought, the index-matching logit will first increase and then remain bounded under mild assumptions.
  arXiv  Detail & Related papers  (2025-09-27T15:23:46Z)
• Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics [69.00587226225232]
  We introduce a state-aware transition framework that abstracts CoT trajectories into structured latent dynamics.<n>To characterize the global structure of reasoning, we model their progression as a Markov chain.<n>This abstraction supports a range of analyses, including semantic role identification, temporal pattern visualization, and consistency evaluation.
  arXiv  Detail & Related papers  (2025-08-29T18:53:31Z)
• Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoning [33.30315111732609]
  Chain of Thought (CoT) reasoning has demonstrated remarkable deep reasoning capabilities.<n>However, its reliability is often undermined by the accumulation of errors in intermediate steps.<n>This paper introduces an approach to calibrate the CoT reasoning accuracy by leveraging the model's intrinsic veracity encoding.
  arXiv  Detail & Related papers  (2025-07-14T07:41:35Z)
• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition [57.51370433303236]
  Chain-of-thought (CoT) reasoning enables large language models to break down complex problems into interpretable intermediate steps.<n>We introduce groundingS, a framework that formulates CoT reasoning as a Markov decision process (MDP) with latent state transitions.<n>We show improvements in reasoning accuracy, diversity, and exploration efficiency across benchmark reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-10T21:32:18Z)
• A Survey on Latent Reasoning [100.54120559169735]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities.<n>CoT reasoning that verbalizes intermediate steps limits the model's expressive bandwidth.<n>Latent reasoning tackles this bottleneck by performing multi-step inference entirely in the model's continuous hidden state.
  arXiv  Detail & Related papers  (2025-07-08T17:29:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.