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.

169,051 papers · 148 categories

Trend · papers per month

89178266355 · Jun 202019922001200920182026
48 results for Natural Language Reasoning

MAC Net improves natural language question answering with data-driven reasoning.

problem Natural Language Question Answering requires complex reasoning.
method MAC Net architecture separates memory and control for iterative reasoning.
result MAC Net achieves high efficiency and interpretability in NLP tasks.

KG-A2C agent learns natural language IF games by reasoning and constraining action spaces.

problem Challenges of natural language understanding, partial observability, and combinatorially large action spaces in IF games.
method Builds a dynamic knowledge graph while exploring, constraining actions using templates.
result Outperforms current IF agents across various games with larger action spaces.

Transformers improve logical reasoning on longer proofs but struggle with length.

problem Understanding systematic generalization in neural proof generation.
method Soft theorem-proving using Transformer models, evaluating logical consistency and inference accuracy.
result Transformers improve generalization with longer proofs but have difficulty with length.

VTA combines verbal and latent reasoning for accurate stock time-series forecasts.

problem Challenges in combining textual analysis with time-series data for financial forecasting.
method Converts stock price data into textual annotations, optimizes reasoning trace using inverse MSE, conditions time-series model outputs on reasoning attributes.
result VTA achieves state-of-the-art forecasting accuracy and interpretable reasoning traces.

PATOIS synthesizes code from natural language using learned code idioms.

problem Synthesizing general-purpose source code from natural language specifications is challenging.
method PATOIS uses a neural synthesizer that interleaves high-level and low-level reasoning, incorporating learned code idioms from a corpus.
result Using learned code idioms improves the synthesizer's accuracy on semantic parsing datasets.

Combines RNNs and tensor products for sequential data, outperforming state-of-the-art.

problem Improving symbolic interpretation and systematic generalization in natural language reasoning.
method End-to-end training of a recurrent neural network architecture with tensor product representations.
result Significantly outperforms state-of-the-art models in natural language reasoning tasks.

LLMs translate natural language trading intents into correct option strategies using a domain-specific language.

problem Challenges in translating natural language trading intents into correct option strategies due to the complexity of option chain data.
method Introduce Option Query Language (OQL) as a domain-specific intermediate representation to abstract option markets into high-level primitives under grammatical rules. Use LLMs as semantic parsers and validate queries by an engine.
result Significantly improves execution accuracy and logical consistency over direct baselines.

The paper fine-tunes language models using human preferences for natural language tasks.

problem Applying reinforcement learning to natural language tasks with human-defined rewards.
method Fine-tuning language models using reward learning techniques, leveraging generative pretraining.
result The approach achieves good results in natural language tasks like text continuation and summarization.

Zero-shot understanding of accidents from surveillance videos using vision-language models

problem Accident understanding from surveillance videos
method Three-stage pipeline with vision-language similarity, metadata-driven multi-prompt reasoning, and entropy-gated pairwise adjudicator
result Substantial improvement in harmonic-mean score over baseline

Learning a natural language interface for database tables is a challenging task that involves deep language understanding and multi-step reasoning. The task is often approached by mapping natural language queries to logical forms or programs that provide the desired response when executed on the database. To our knowle…

2016-11-28abs ↗pdf ↗

FINCH dataset enables financial Text-to-SQL tasks, improving model evaluation.

problem Lack of a large-scale financial dataset for Text-to-SQL tasks.
method Curated financial dataset (FINCH), benchmarking reasoning and language models.
result Proposed FINCH Score for more accurate financial model evaluation.

Self-supervised skip-tree training improves mathematical reasoning in language models.

problem Improving logical reasoning in language models for formal mathematics.
method Self-supervised language modeling on mathematical formulas, skip-tree task.
result Models trained on skip-tree task outperform standard models in mathematical reasoning tasks.

Study of sentence representations in AI shows parallels to human learning.

problem Understanding how AI systems learn and generalize from training data.
method Diagnostic tests, performance analysis, training distribution effects, representation changes with augmentations.
result AI systems can learn abstract rules and generalize under certain conditions, similar to human zero-shot reasoning.

Deep Sets improve reinforcement learning agent's object-centered navigation and generalization.

problem Improving reinforcement learning agents' ability to generalize to unseen objects and goals.
method Combining object-wise permutation invariant networks (Deep Sets) and gated-attention mechanisms.
result Agent demonstrates strong generalization to out-of-distribution goals in a procedurally-generated 2D world.

Large language models can't efficiently reason conditionally in a distribution-free setting.

problem Impossibility of conditional PAC-efficient reasoning in large language models.
method Proof of impossibility in a distribution-free setting for non-atomic input spaces.
result Any algorithm achieving conditional PAC efficiency must defer to the expert model with high probability.

New language model shows context length impacts generation quality and reasoning ability.

problem Analyzing the impact of context length and reasoning on autoregressive generation.
method Introduced synthetic hierarchical languages, used an exact k-gram ansatz, derived asymptotic predictions, and validated empirically.
result Reasoning models with limited context can generate sequences from the true language, improving exponentially over standard models.

Method guarantees coherent factuality for language model outputs in reasoning tasks.

problem Ensuring correctness of language model outputs in reasoning tasks.
method Developed a conformal-prediction-based method applied to subgraphs within a deducibility graph.
result Achieved coherent factuality across target coverage levels, 90% on stricter definition.

The study compares feed-forward and attention layers in language models.

problem Understanding the role of feed-forward and attention layers in language models.
method Empirical and theoretical analysis in a synthetic setting.
result Feed-forward layers learn simple distributional associations, while attention layers focus on in-context reasoning.

LaTRO optimizes latent reasoning in LLMs without external reward.

problem Training LLMs to perform complex reasoning tasks.
method Formulates reasoning as latent distribution sampling and optimizes via variational approaches.
result LLMs improve reasoning and evaluation quality through self-improvement.

A novel method for visual question answering using scene graphs and reinforcement learning.

problem Answering free-form questions about images with deep linguistic and visual understanding.
method Context-driven, sequential reasoning based on scene graphs and reinforcement learning.
result Our method almost reaches human performance on the GQA dataset.

Paper explores why compositionality is not the right approach for emergent communication.

problem Lack of interaction between biological and computational models of emergent communication.
method Exploring the claim that compositionality is the wrong target for explaining natural language emergence.
result Suggests reflexivity as a better target for explaining natural language emergence.

Platform combines RL and language models to study narrative influence on AI decisions.

problem Understanding how narrative elements shape AI decision-making.
method Dual-system architecture with reinforcement learning and language model integration.
result Initial experiments show narrative frameworks can influence AI decision-making.

Enhances large language models' reasoning through simpler off-policy reinforcement learning.

problem Improving large language models' ability to reason and solve problems.
method EM Policy Gradient, optimizing expected return over reasoning trajectories using Expectation-Maximization (EM) optimization.
result Achieves comparable or slightly superior performance to state-of-the-art methods on reasoning datasets, with additional cognitive behaviors.

FLUID-LLM uses LLMs to predict fluid dynamics with improved accuracy.

problem Leveraging LLMs for CFD due to their pattern recognition abilities but struggles with fluid dynamics complexities.
method Combines pre-trained LLMs with spatiotemporal-aware encoding to predict unsteady fluid dynamics.
result Significant performance improvements in CFD predictions across various datasets.

Unified model learns concepts across domains like left and right.

problem Limited generalization of language concepts in inference-only models.
method Logic-Enhanced Foundation Model (LEFT) with a differentiable, domain-independent program executor.
result LEFT flexibly learns and reasons with concepts across 2D images, 3D scenes, human motions, and robotic manipulation.

Proposes CLRS-Text, a new benchmark for evaluating LM reasoning capabilities.

problem Lack of transferable benchmarks for evaluating reasoning capabilities of language models.
method Developed a textual version of the CLRS benchmark, generating diverse algorithmic tasks.
result Demonstrates a novel challenge for the LM reasoning community and validates prior work.

This work investigates how multi-round reasoning improves LLM performance.

problem Improving problem-solving abilities in complex tasks with LLMs.
method Investigates approximation, learnability, and generalization properties of multi-round auto-regressive models.
result Transformers with finite context windows are universal approximators for Turing-computable functions and can approximate any Turing-computable sequence-to-sequence function through multi-round reasoning.

This study explains RL training dynamics in LLMs, focusing on token-level optimization and reasoning pattern reshaping.

problem Understanding the training dynamics of RL in LLMs to improve their reasoning capabilities.
method Empirical analysis and theoretical modeling of RL training process, focusing on reasoning patterns and token optimization.
result RL primarily optimizes a sparse subset of critical tokens, reshaping reasoning pattern distributions and affecting model performance.

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.

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.

Trade-R1 bridges verifiable rewards to stochastic financial markets via process-level reasoning verification.

problem Extending RL to financial markets where rewards are verifiable but noisy.
method A verification method that transforms reasoning over financial documents into a structured RAG task, using a triangular consistency metric.
result DSR achieves superior cross-market generalization while maintaining reasoning consistency.

FinHEAR combines LLMs with human expertise for better financial decision-making.

problem Challenges in financial decision-making for language models.
method Multi-agent framework with specialized LLMs for historical analysis, event interpretation, and expert retrieval.
result FinHEAR outperforms baselines in financial tasks with higher accuracy and risk-adjusted returns.

Neural models use default reasoning for number and gender assignment tasks.

problem Understanding how neural language models make decisions for grammatical phenomena.
method Generalised Contextual Decomposition (GCD) to isolate semantic, syntactic, and bias-driven components of predictions.
result Models rely on default reasoning for tasks like number and gender assignment.

Graph signal processing detects hallucinations in large language models.

problem Detecting factual reasoning from hallucinations in large language models.
method Modeling transformer layers as dynamic graphs, using spectral analysis to define diagnostics.
result Spectral signatures can distinguish different types of hallucinations and achieve high accuracy.

Natural language processing improves COVID-19 hospitalization identification.

problem Identifying patients hospitalized due to COVID-19 among those with positive SARS-CoV-2 tests.
method Used natural language processing on provider notes and structured EHR data elements to create classification algorithms.
result Classification algorithms using provider notes outperformed those using only structured EHR data elements, with AUROC of 0.894 compared to 0.841.