Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

6481,2961,9442,592 · Jun 202019922001200920172026
48 results for chain of thought

A method for learning with autoregressive chain-of-thoughts.

problem Learning prompt-to-answer mappings from sequence-to-next-token generators.
method Iterating a fixed, time-invariant generator for multiple steps to generate a chain-of-thought, then taking the final token as the answer.
result Universal representability and computationally tractable chain-of-thought learning for a simple base class.

AI systems that explain their decisions can be monitored for harmful intentions.

problem Monitoring AI systems' decision-making processes for harmful intentions is imperfect and can miss some misbehavior.
method Monitoring the chain of thought (CoT) of AI systems that communicate in human language.
result CoT monitoring is a promising but fragile approach to AI safety.

Optimal sample complexity for autoregressive chain-of-thought learning proven.

problem Determining the minimum number of samples needed for accurate autoregressive chain-of-thought learning.
method Proved upper bound on sample complexity using Daniely-Shalev-Shwartz dimension and roll-out stable parity dimension.
result The sample complexity is bounded by the local next-token class rate, with no dependence on rollout length.

Transformers solve parity problems efficiently with step-by-step reasoning.

problem Training transformers to solve complex, recursive problems like parity.
method Training a one-layer transformer to solve kk-parity, incorporating intermediate parities into the loss function, and using teacher forcing or augmented data.
result Transformers can learn parity in one gradient update with intermediate supervision or self-consistency checks.

Transformers learn chain-of-thought reasoning for longer problems, proving length generalization.

problem Challenging problems require deeper reasoning, but how do models generalize this to longer tasks?
method Theoretical analysis of transformers on synthetic state-tracking tasks, proving length generalization through attention concentration.
result Transformers can learn chain-of-thought reasoning for longer problems, proving length generalization.

Prefix consistency improves model reliability by weighting answers based on their reproducibility.

problem Improving the reliability of large language models' reasoning traces.
method Use prefix consistency to weight candidate answers based on their reproducibility during regeneration.
result Prefix consistency is the best correctness predictor, reaching Standard MV plateau accuracy with up to 21x fewer tokens.

This paper improves learning complex functions with CoT supervision, reducing sample complexity.

problem Learning complex functions with multi-step reasoning.
method Develops a statistical theory linking CoT risk and end-to-end risk, using CoT information measure.
result CoT supervision can achieve significantly faster learning rates compared to standard E2E supervision.

Theoretical work shows integrating coherent reasoning improves LLM performance and error correction.

problem Improving reasoning and error correction in large language models (LLMs) with few-shot prompting.
method Theoretical analysis and sensitivity experiments on transformer behavior with coherent reasoning and corrupted demonstrations.
result The transformer gains better error correction ability and more accurate predictions when coherent reasoning is integrated.

Summarizes financial news for better investment decisions.

problem Information overload from financial news hinders timely investment decisions.
method Personalized Chain-of-Thought summarization framework integrating user-specified keywords.
result Personalized summaries highlight relevant market signals, improving investment narratives.

Study reveals how depth of reasoning affects generalization in models.

problem Understanding scaling behavior of generalization with CoT depth.
method Theoretical model of CoT in linear regression using random matrix theory.
result Sharp phase transition between exponential and polynomial improvement, saturation, and overthinking.

CoT-UQ improves LLM uncertainty quantification by integrating reasoning steps.

problem LLMs' overconfidence and lack of response-wise uncertainty quantification.
method Integrates LLMs' reasoning steps into uncertainty estimation.
result Significantly improves uncertainty quantification accuracy (5.9% AUROC improvement).

Fractured Sampling improves LLM reasoning efficiency by truncating CoT trajectories.

problem Efficiently scaling reasoning in large language models with limited tokens.
method Integrating truncated Chain-of-Thought (CoT) with Fractured Sampling across multiple dimensions.
result Fractured Sampling achieves superior accuracy-cost trade-offs compared to full CoT.

This work analyzes CoT prompting methods from a statistical estimation perspective.

problem Improving the effectiveness of LLMs in solving multi-step reasoning problems.
method Introducing a multi-step latent variable model to characterize CoT prompting from a statistical estimation viewpoint.
result The CoT estimator is equivalent to a Bayesian estimator when the pretraining dataset is large.

The paper studies how search and distillation improve reasoning in large language models.

problem Improving reasoning capabilities of large language models.
method Viewing chain-of-thought generation as a metastable Markov process, proving benefits of search and distillation.
result Search protocol rewards sparse edges, reducing the expected number of steps to reach different clusters.

The paper explores how LLMs with CoT improve performance on complex tasks.

problem Understanding the mechanisms behind LLMs' improved performance with CoT.
method Using circuit complexity theory, the paper examines LLMs' expressivity in solving mathematical and decision-making problems.
result LLMs with CoT can generate correct solutions step-by-step, even for complex tasks.

CoT enhances transformer accuracy on serial tasks by enabling serial computation.

problem Improving accuracy of large language models on inherently serial problems.
method Integrating a chain of thought (CoT) into decoder-only transformers to enable serial computation.
result Constant-depth transformers with CoT can solve problems in AC^0, surpassing TC^0 without CoT.

A conformal procedure improves CoT reasoning by aggregating reasoning paths and calibrating abstention rules.

problem Aggregation uncertainty in chain-of-thought reasoning makes correct answers less reliable.
method Introduces a conformal procedure for CoT reasoning that uses weighted score aggregation and abstention rules.
result Achieves higher selective accuracy with abstention, reducing confident-error rate.

A new method for math reasoning that allows for iterative correction.

problem Standard reasoning models commit to each token and cannot recover from early errors.
method Generative framework with latent thought vectors for iterative self-correction.
result 30 rethinking iterations surpass baselines with 15 times more parameters.

CoT improves transformer sample efficiency by reducing input token dependencies and attention sparsity.

problem Transformer sample inefficiency in simple tasks.
method Demonstrated through parity-learning setup, showing CoT reduces required samples from exponential to polynomial.
result Transformer learns function within polynomial samples with CoT, requiring exponential samples without CoT.

Transformers can generalize to a large task family with only a few demonstrations.

problem Can learning from a small set of tasks generalize to a large task family?
method Investigating autoregressive compositional structure where each task is a composition of TT operations, each from a finite family of DD subtasks.
result Transformers can generalize to DTD^T tasks with only O~(D)\widetilde{O}(D) demonstrations.

Dynamic abstention improves LLM accuracy by selectively terminating unpromising reasoning.

problem LLMs waste compute on incorrect responses, leading to inefficiency.
method Formal reinforcement learning framework with abstention reward parameter.
result Dynamic abstention outperforms natural baselines in selective accuracy.

LaRT models LLMs' response accuracy and CoT length to evaluate reasoning ability and speed.

problem Valid evaluation of Large Language Models (LLMs) via response accuracy and chain-of-thought length.
method Introduces Latency-Response Theory (LaRT) to jointly model response accuracy and CoT length using latent ability and latent speed.
result LaRT yields higher estimation accuracy and shorter confidence intervals for latent traits compared to IRT.

RNNs struggle with in-context retrieval, while Transformers excel.

problem In-context retrieval capability of RNNs.
method Theoretical analysis and experimental techniques (CoT, RAG, Transformer layer).
result Enhancing RNNs with techniques improves their in-context retrieval capability, closing the representation gap with Transformers.

Transformers struggle with time series forecasting, especially in context.

problem Transformers' limitations in time series forecasting, particularly in in-context settings.
method Theoretical analysis of Transformers' limitations through In-Context Learning theory.
result Linear Self-Attention models cannot outperform classical linear models in in-context time series forecasting.

Reasoning models generate differently based on problem difficulty, not just length.

problem Understanding how reasoning models handle different problem difficulties.
method Examined hidden-state trajectories across competitive programming, mathematics, and Boolean satisfiability.
result Corrected trajectory geometry shows difficulty-dependent differences in reasoning models, with stronger effects in the code domain.

Transformers learn multi-step reasoning through gradient descent.

problem Understanding how transformers solve symbolic multi-step reasoning tasks.
method Theoretical analysis of gradient descent dynamics and multi-phase training.
result Trained one-layer transformers can solve both backward and forward reasoning tasks with generalization guarantees.

Knot theory applied to proteins, distinguishing folded linear chains.

problem Classifying proteins as unknots when intra-chain interactions are ignored.
method Developing knot theory for folded linear molecular chains, considering self-bonding, and using Gauss codes and quandles.
result Extended knot theory to distinguish topologies of proteins with intra-chain bonds.

Given an n-manifold M and an n-category C, we define a chain complex (the "blob complex") B_*(M;C). The blob complex can be thought of as a derived category analogue of the Hilbert space of a TQFT, and as a generalization of Hochschild homology to n-categories and n-manifolds. It enjoys a number of nice formal properti…

2010-09-25abs ↗pdf ↗

Directed acyclic graphs are the basic representation of the structure underlying Bayesian networks, which represent multivariate probability distributions. In many practical applications, such as the reverse engineering of gene regulatory networks, not only the estimation of model parameters but the reconstruction of t…

2012-02-29abs ↗pdf ↗

Langevin Dynamics speeds up mixing time with manifold hypothesis and multi-scale approach.

problem Langevin Dynamics struggles in high dimensions and nonconvex landscapes.
method Utilizes manifold hypothesis to reduce mixing time and employs multi-scale approach to improve image generation quality.
result Mixing time depends on intrinsic dimension rather than ambient dimension, significantly reducing computational complexity.

Transformers learn sparse Boolean functions through RL and SFT, revealing distinct learning behaviors.

problem Learning sparse Boolean functions with Transformers.
method Reinforcement Learning (RL) with process rewards and Supervised Fine-Tuning (SFT).
result RL learns the whole CoT chain simultaneously, while SFT learns step by step.

Protein Thoughts interprets protein interactions with clear reasoning, improving prediction accuracy.

problem Lack of mechanistic justification in protein-protein interaction predictions.
method Interpretable search problem reformulation, hypothesis-guided entropy-regularized Tree-of-Thoughts search, embedding-space flow matching.
result Improves mean best-binder rank from 47.7 to 11.2 on SHS148k benchmark.

LLMs struggle with financial reasoning but can outperform the market with human oversight.

problem Financial reasoning failures in LLM-generated stock market predictions.
method Evaluated four LLMs using three prompting strategies and compared to human oversight.
result LLMs require human oversight to fully realize their potential in financial markets.

Study compares MCMC and nested sampling for high-dimensional physics problems.

problem Efficiently sampling high-dimensional Bayesian posterior distributions in particle physics and cosmology.
method Review and comparison of MCMC and nested sampling techniques on high-dimensional test functions and real physics examples.
result Modern MCMC algorithms can outperform nested sampling in certain cases, highlighting implementation details.

This paper continues the study of decompositions of a smooth 4-manifold into two handlebodies with handles of index 2\leq2. Part I gave existence results in terms of spines and chain complexes over the fundamental group of the ambient manifold. Here we assume that one side of a decomposition has larger fundamental gro…

2001-09-20abs ↗pdf ↗

The data torrent unleashed by current and upcoming astronomical surveys demands scalable analysis methods. Many machine learning approaches scale well, but separating the instrument measurement from the physical effects of interest, dealing with variable errors, and deriving parameter uncertainties is often an after-th…

2017-07-14abs ↗pdf ↗