Pith. sign in

REVIEW 23 cited by

Chain of Thought Empowers Transformers to Solve Inherently Serial Problems

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.12875 v4 pith:7GCFEYXM submitted 2024-02-20 cs.LG cs.CCstat.ML

Chain of Thought Empowers Transformers to Solve Inherently Serial Problems

classification cs.LG cs.CCstat.ML
keywords transformersmathsfproblemssolveconstant-depthprecisionsizeaccuracy
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Instructing the model to generate a sequence of intermediate steps, a.k.a., a chain of thought (CoT), is a highly effective method to improve the accuracy of large language models (LLMs) on arithmetics and symbolic reasoning tasks. However, the mechanism behind CoT remains unclear. This work provides a theoretical understanding of the power of CoT for decoder-only transformers through the lens of expressiveness. Conceptually, CoT empowers the model with the ability to perform inherently serial computation, which is otherwise lacking in transformers, especially when depth is low. Given input length $n$, previous works have shown that constant-depth transformers with finite precision $\mathsf{poly}(n)$ embedding size can only solve problems in $\mathsf{TC}^0$ without CoT. We first show an even tighter expressiveness upper bound for constant-depth transformers with constant-bit precision, which can only solve problems in $\mathsf{AC}^0$, a proper subset of $ \mathsf{TC}^0$. However, with $T$ steps of CoT, constant-depth transformers using constant-bit precision and $O(\log n)$ embedding size can solve any problem solvable by boolean circuits of size $T$. Empirically, enabling CoT dramatically improves the accuracy for tasks that are hard for parallel computation, including the composition of permutation groups, iterated squaring, and circuit value problems, especially for low-depth transformers.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 23 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought

    cs.LG 2026-07 accept novelty 8.0

    The sample complexity of exact-trace learning for autoregressive Chain-of-Thought is O((DSdim(H) + log(1/δ))/ε), matching the local next-token class with no dependence on rollout length.

  2. Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete

    cs.LG 2026-06 unverdicted novelty 8.0

    Sliding-window transformers without positional encodings are Turing complete because the sliding window breaks permutation symmetry and suffices to simulate Post machines via a constant-size histogram state.

  3. Transformers Provably Learn to Internalize Chain-of-Thought

    cs.LG 2026-05 unverdicted novelty 8.0

    L-layer transformers under Log-ICoT curriculum provably learn k-parity with poly(n) samples and log k stages, matching explicit CoT efficiency without inference overhead.

  4. Forecasting Future Behavior as a Learning Task

    cs.AI 2026-06 unverdicted novelty 7.0

    Behavior Forecasters trained on LRM trajectories outperform larger models in predicting repeatability and input sensitivity at low cost.

  5. Agentic Transformers Provably Learn to Search via Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 7.0

    In a stochastic k-ary tree, a two-head transformer learns randomized DFS via policy gradient under depth-wise curriculum, generalizes to deeper trees, and adapts to imbalanced goals via discounting.

  6. Learned Relay Representations for Forward-Thinking Discrete Diffusion Models

    cs.LG 2026-05 unverdicted novelty 7.0

    Learned Relay Representations enable masked diffusion models to propagate useful latent information across denoising steps, scaling to Fast-dLLM v2 to outperform supervised finetuning on coding tasks while cutting inf...

  7. PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media

    cs.CL 2026-05 unverdicted novelty 7.0

    PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic onlin...

  8. Training Transformers as a Universal Computer

    cs.AI 2026-04 unverdicted novelty 7.0

    A transformer trained on random meaningless MicroPy programs generalizes to execute diverse human-written programs, providing empirical evidence it can act as a universal computer.

  9. Internalized Reasoning for Long-Context Visual Document Understanding

    cs.CV 2026-03 unverdicted novelty 7.0

    A synthetic pipeline creates and internalizes reasoning traces in VLMs for long-context visual document understanding, with a 32B model surpassing a 235B model on MMLongBenchDoc and showing 12.4x fewer output tokens.

  10. Training Large Language Models to Reason in a Continuous Latent Space

    cs.CL 2024-12 unverdicted novelty 7.0

    Coconut lets LLMs perform reasoning directly in continuous latent space by recycling hidden states as inputs, outperforming standard chain-of-thought on search-intensive logical tasks with better accuracy-efficiency t...

  11. Internalized Reasoning for Long-Context Visual Document Understanding

    cs.CV 2026-03 conditional novelty 6.5

    Synthetic page-ranked reasoning traces plus low-strength model merging give a 32B VLM 58.3 on MMLongBenchDoc, beating a 235B teacher while cutting output tokens ~12× versus explicit reasoning.

  12. Learned Relay Representations for Forward-Thinking Discrete Diffusion Models

    cs.LG 2026-05 unverdicted novelty 6.0

    Learned Relay Representations add a differentiable per-token channel to masked diffusion models so they can propagate latent information across iterative denoising steps, yielding better coding performance and up to 3...

  13. Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute

    cs.AI 2026-05 unverdicted novelty 6.0

    Diverse ensembles of prompted and fine-tuned GPT-4.1-Mini monitors achieve 2.4x better detection of flawed code solutions than homogeneous ensembles on adversarial inputs.

  14. The Power of Power Law: Asymmetry Enables Compositional Reasoning

    cs.AI 2026-04 unverdicted novelty 6.0

    Power-law data distributions outperform uniform ones for compositional reasoning by creating asymmetry that lets frequent skill compositions scaffold rare ones with less data.

  15. The Power of Power Law: Asymmetry Enables Compositional Reasoning

    cs.AI 2026-04 unverdicted novelty 6.0

    Power-law data sampling creates beneficial asymmetry in the loss landscape that lets models acquire high-frequency skill compositions first, enabling more efficient learning of rare long-tail skills than uniform distr...

  16. HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering

    cs.AI 2026-04 unverdicted novelty 6.0

    HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.

  17. Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agents

    cs.AI 2026-03 conditional novelty 6.0

    A community-maintained, schema-standardized toolbox with continuous intrinsic-tool evaluation yields 6–22% relative gains over a curated baseline across multiple LLM agent architectures.

  18. Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning

    cs.RO 2026-02 unverdicted novelty 6.0

    R&B-EnCoRe uses self-supervised importance-weighted variational inference to distill action-predictive reasoning datasets that improve VLA performance on manipulation, navigation, and driving tasks without external verifiers.

  19. NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning

    cs.LG 2026-05 unverdicted novelty 5.0

    Injecting noise into LLM latent trajectories creates diverse reasoning paths whose agreement acts as a confidence signal for selective abstention, cutting error rates from 40-70% to under 15% on math tasks.

  20. LLM Reasoning Is Latent, Not the Chain of Thought

    cs.AI 2026-04 unverdicted novelty 5.0

    LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.

  21. The Serial Scaling Hypothesis

    cs.LG 2025-07 unverdicted novelty 5.0

    The serial scaling hypothesis formalizes inherently serial problems in complexity theory and demonstrates that diffusion models cannot solve them.

  22. Lost in Cultural Translation: Do LLMs Struggle with Math Across Cultural Contexts?

    cs.AI 2025-03 conditional novelty 5.0

    LLMs show accuracy drops of 0.3% to 5.9% on GSM8K math problems when culturally adapted to six countries while keeping math operations identical, with statistical significance confirmed by McNemar tests.

  23. Measuring AI Reasoning: A Guide for Researchers

    cs.AI 2026-05 unverdicted novelty 4.0

    Reasoning in language models should be measured by the faithfulness and validity of their multi-step search processes and intermediate traces, not final-answer accuracy.