The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models

• URL: http://arxiv.org/abs/2604.06374v1
• Date: Tue, 07 Apr 2026 18:59:32 GMT
• Title: The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models
• Abstract summary: We investigate whether language models actually leverage superposition when reasoning using latent CoTs.<n>We find that only models trained from scratch exhibit signs of using superposition.<n>Our results offer a unified explanation for when and why superposition arises in continuous chain-of-thought reasoning.
• Score: 15.12701445445687
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Latent reasoning via continuous chain-of-thoughts (Latent CoT) has emerged as a promising alternative to discrete CoT reasoning. Operating in continuous space increases expressivity and has been hypothesized to enable superposition: the ability to maintain multiple candidate solutions simultaneously within a single representation. Despite theoretical arguments, it remains unclear whether language models actually leverage superposition when reasoning using latent CoTs. We investigate this question across three regimes: a training-free regime that constructs latent thoughts as convex combinations of token embeddings, a fine-tuned regime where a base model is adapted to produce latent thoughts, and a from-scratch regime where a model is trained entirely with latent thoughts to solve a given task. Using Logit Lens and entity-level probing to analyze internal representations, we find that only models trained from scratch exhibit signs of using superposition. In the training-free and fine-tuned regimes, we find that the superposition either collapses or is not used at all, with models discovering shortcut solutions instead. We argue that this is due to two complementary phenomena: i) pretraining on natural language data biases models to commit to a token in the last layers ii) capacity has a huge effect on which solutions a model favors. Together, our results offer a unified explanation for when and why superposition arises in continuous chain-of-thought reasoning, and identify the conditions under which it collapses.

Related papers

• Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression [42.15219720606396]
  Large language models achieve high reasoning performance via explicit chain-of-thought and reinforcement learning.<n>Latent reasoning reduces this cost by shifting computation into a latent space.<n>We propose textbfDiscrete Latent Reasoning(DLR), the first method that converts continuous latent states into explicit discrete tokens.
  arXiv  Detail & Related papers  (2026-06-29T02:34:52Z)
• Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models [0.0]
  Chain-of-Thought (CoT) reasoning has emerged as a key technique for eliciting complex reasoning in Large Language Models (LLMs)<n>We introduce MoralChain, a benchmark of 12,000 social scenarios with parallel moral/immoral reasoning paths.<n>We show that continuous thought models can exhibit misaligned latent reasoning while producing aligned outputs.
  arXiv  Detail & Related papers  (2026-04-25T22:43:15Z)
• Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens [13.653741247835091]
  Latent Thoughts Tuning (LT-Tuning) is a framework that redefines how latent thoughts are constructed and deployed.<n>We introduce a Context-Prediction-Fusion mechanism that jointly leveraging contextual hidden states and predictive semantic guidance.<n>Our method outperforms existing latent reasoning baselines, effectively mitigating feature collapse and achieving robust reasoning accuracy.
  arXiv  Detail & Related papers  (2026-02-10T19:19:10Z)
• Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization [9.193078163792427]
  Chain-of-Thought (CoT) empowers Large Language Models (LLMs) to tackle complex problems.<n>Recent latent reasoning approaches attempt to optimize efficiency by performing reasoning within continuous hidden states.<n>We introduce PLaT, a framework that reformulates latent reasoning as planning by fundamentally decouple reasoning from verbalization.
  arXiv  Detail & Related papers  (2026-01-29T07:38:18Z)
• Temporal Predictors of Outcome in Reasoning Language Models [0.0]
  Chain-of-thought (CoT) paradigm uses the elicitation of step-by-step rationales as a proxy for reasoning.<n>We show that, for harder questions, a drop in predictive accuracy highlights a selection artifact.<n>Overall, our results imply that for reasoning models, internal self-assessment of success tends to emerge after only a few tokens.
  arXiv  Detail & Related papers  (2025-11-03T08:57:18Z)
• 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)
• A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models [58.32070787537946]
  Chain-of-thought (CoT) reasoning enhances performance of large language models.<n>We present the first comprehensive study of CoT faithfulness in large vision-language models.
  arXiv  Detail & Related papers  (2025-05-29T18:55:05Z)
• Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space [62.54887038032942]
  We introduce Soft Thinking, a training-free method that emulates human-like "soft" reasoning by generating soft, abstract concept tokens.<n>These concept tokens are created by the probability-weighted mixture of token embeddings, which form the continuous concept space.<n>In essence, each generated concept token encapsulates multiple meanings from related discrete tokens, implicitly exploring various reasoning paths to converge.
  arXiv  Detail & Related papers  (2025-05-21T17:29:15Z)
• Training Large Language Models to Reason in a Continuous Latent Space [71.0274000348354]
  We introduce a new paradigm called Coconut (Chain of Continuous Thought) to explore the potential of reasoning beyond language.<n>Instead of decoding this state into words, we feed it back to the model as the next input embedding directly in the continuous space.<n>This latent reasoning paradigm enables an advanced reasoning pattern, where continuous thoughts can encode multiple alternative next steps.
  arXiv  Detail & Related papers  (2024-12-09T18:55:56Z)
• Conceptual and Unbiased Reasoning in Language Models [98.90677711523645]
  We propose a novel conceptualization framework that forces models to perform conceptual reasoning on abstract questions. We show that existing large language models fall short on conceptual reasoning, dropping 9% to 28% on various benchmarks. We then discuss how models can improve since high-level abstract reasoning is key to unbiased and generalizable decision-making.
  arXiv  Detail & Related papers  (2024-03-30T00:53:53Z)
• Implicit Chain of Thought Reasoning via Knowledge Distillation [58.80851216530288]
  Instead of explicitly producing the chain of thought reasoning steps, we use the language model's internal hidden states to perform implicit reasoning. We find that this approach enables solving tasks previously not solvable without explicit chain-of-thought, at a speed comparable to no chain-of-thought.
  arXiv  Detail & Related papers  (2023-11-02T17:59:49Z)

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.