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.

168,695 papers · 148 categories

Trend · papers per month

3587161,0731,431 · Jun 202019922001200920172026
48 results for Causal language models

New methods predict language model out-of-distribution behaviors using causal mechanisms.

problem Predicting how language models behave on unseen data.
method Two methods: counterfactual simulation and value probing.
result Both methods achieve high AUC-ROC and outperform causal-agnostic approaches in out-of-distribution settings.

Language models trained on chess board states outperform those on moves, even with causal masking.

problem Applying causal masking to spatial data for training unimodal language models.
method Trained bidirectional and causal self-attention models on both spatial (board-based) and sequential (move-based) chess data.
result Models trained on spatial board states achieve stronger playing strength than those trained on sequential data, even with causal masking.

New study finds best language model architecture and pretraining objective for zero-shot tasks.

problem Evaluating which language model architectures and pretraining objectives best enable zero-shot generalization.
method Compared three model architectures and two pretraining objectives across 170 billion tokens, with and without finetuning.
result Causal decoder-only models trained on autoregressive language modeling exhibit strongest zero-shot generalization.

The study uncovers latent capabilities of language models via causal representation learning.

problem Rigorous causal evaluations of language model capabilities are challenging due to confounding effects and computational costs.
method Proposes a causal representation learning framework to identify latent capability factors as causally interrelated after controlling for a common confounder (base model).
result Identifies a three-node linear causal structure explaining performance variations across 1500 models and six benchmarks.

Unified framework for ICL in causal and masked models.

problem Understanding ICL in masked language models and comparing it to causal models.
method Developed a statistical learning framework representing context by empirical measure and predicting using context and query.
result Upper bounds for masked and autoregressive objectives under Wasserstein-type regularity conditions.

LLM4Causal democratizes causal reasoning via fine-tuned LLMs.

problem Limited capability of LLMs in causal inference and interpretation.
method Fine-tuning an open-source LLM for causal tasks, proposing datasets for instruction tuning.
result LLM4Causal delivers end-to-end solutions for causal problems and interprets results easily.

Triangulation filters spurious circuits in multilingual models.

problem Unreliable explanations of multilingual models across languages.
method Formalizes reference families and introduces triangulation as a causal acceptance rule.
result Triangulation provides a falsifiable standard for mechanistic claims.

Paper develops a new inequality for non-causal machine learning.

problem Current concentration inequalities cannot be applied to non-causal machine learning.
method Develops a framework for non-causal random fields and proves a Hoeffding-type inequality.
result Obtains a Hoeffding-type concentration inequality for non-causal random fields.

A new approach to rationalization identifies true rationales by considering causal relationships.

problem Existing rationalization methods struggle with spuriousness, where snippets with similar contributions are hard to distinguish.
method The method leverages causal inference to identify non-spurious rationales, defining probabilities of causation based on a structural causal model.
result The proposed causal rationalization outperforms existing methods on real-world datasets.

This paper integrates LLMs into SCD to improve causal inference accuracy.

problem Challenges in acquiring domain expert knowledge for causal models.
method Statistical causal prompting (SCP) for LLMs and prior knowledge augmentation for SCD.
result LLM-KBCI and SCD augmented with LLM-KBCI approach ground truths more closely.

Does adding a theorem to a paper affect its chance of acceptance? Does labeling a post with the author's gender affect the post popularity? This paper develops a method to estimate such causal effects from observational text data, adjusting for confounding features of the text such as the subject or writing quality. We…

2019-05-29abs ↗pdf ↗

Benchmark assesses LLMs' causal inference skills, revealing significant limitations.

problem Lack of rigorous evaluation of LLMs' causal inference capabilities.
method CausalPitfalls benchmark with structured challenges and grading rubrics.
result Significant limitations in current LLMs' statistical causal inference.

AI uses language models to find instrumental variables quickly.

problem Finding valid instrumental variables is a challenging and heuristic process.
method Uses large language models to search for new instrumental variables through narratives and counterfactual reasoning.
result Demonstrates the effectiveness of multi-step and role-playing prompting strategies for LLMs.

Two environments are enough to infer causal graphs and counterfactuals.

problem Inferring causal relations from multiple environments, especially for nonlinear mechanisms.
method Using structural causal models and the invariance principle, the study shows that only two auxiliary environments are sufficient for causal graph inference and counterfactual inference.
result Two auxiliary environments are sufficient for identifying causal graphs and counterfactuals.

Meta-Router optimizes LLM selection using gold-standard and preference-based data.

problem Training a high-quality LLM router with combined data sources is challenging due to bias and scarcity.
method Developed an integrative causal router training framework to correct bias and improve routing accuracy.
result Our approach delivers more accurate routing and improves the trade-off between cost and quality.

Develops geometric causal models for causal inference from dependent data.

problem Causal inference from structured, dependent data (e.g., spatial, network, molecular).
method Geometric causal models (GCMs) exploiting symmetries of data generating process, combining group theory, ergodic theory, and Bayesian inference.
result Establishes identification and estimation of causal effects from dependent data.

LLMs detect market patterns through causal reasoning, not just temporal association.

problem Detecting structural market patterns in financial data.
method Obfuscation testing using the WHO-WHOM-WHAT framework.
result LLMs achieve 71.5% detection rate of market patterns without temporal context.

This paper uses LLMs for causal discovery with active learning and dynamic scoring to improve efficiency and fairness.

problem High computational demands and complexities of large-scale data in causal discovery.
method Metadata-based approach, BFS strategy, Active Learning, Dynamic Scoring Mechanism, LLM confidence scores.
result Significantly reduced number of queries and improved efficiency in causal graph construction.

CaTs use DAGs with transformers to enforce causal constraints, improving neural network robustness.

problem Neural networks lack inherent causal structure respect, leading to reliability issues.
method Introducing Causal Transformers (CaTs) that operate under predefined causal constraints specified by DAGs.
result CaTs improve robustness and interpretability of neural networks under causal constraints.

Unified approach to learn interpretable concepts from data.

problem Building interpretable machine learning models and highly-performing foundation models.
method Relating causal representation learning and foundation models, defining concepts and proving their recoverability.
result Provable recovery of human-interpretable concepts from diverse data.

Researchers identify latent variables and causal structures from nonlinear hierarchical models.

problem Challenging task of identifying latent variables and causal structures from observational data, especially when relationships are nonlinear.
method Investigated nonlinear latent hierarchical causal models, developed identification criterion, and constructed an estimation procedure.
result Identifiability of causal structures and latent variables achieved under mild assumptions.

CausalGame benchmarks LLM agents' causal thinking in games.

problem Evaluating causal thinking in AI Scientists with LLMs.
method Interactive games with 14 scenarios incorporating selection bias, measurement error, and hidden confounders.
result None of the 30 LLM agents demonstrated reliable causal thinking, with the best model achieving only 68.0% survival.

Study evaluates large language models' ability to understand probabilistic real-world distributions.

problem Understanding how LLMs grasp probabilistic knowledge of real-world distributions.
method Developed a benchmark to test LLMs' ability to learn and represent empirical distributions across various domains.
result LLMs perform poorly in understanding real-world statistics and do not naturally internalize these distributions.

CausalEvolve improves efficiency and discovery in open-ended scientific tasks.

problem Lack of targeted guidance and knowledge organization in evolve-based agents.
method Causal scratchpad that identifies and reasons about guiding factors for evolution.
result Effective improvement in evolutionary efficiency and better solutions.

New method detects bias in AI models that generate data.

problem Detecting bias in AI models that generate data.
method Formalized causal fairness in generative AI, derived new decomposition results, established identification conditions, and introduced efficient estimators.
result Demonstrated the value of new methodology in analyzing bias in large language models.

L2D-CD learns to defer expert recommendations in causal discovery.

problem Combining expert knowledge with data-driven results in causal discovery when expert recommendations may contradict data.
method Adapting learning-to-defer algorithms for pairwise causal discovery, L2D-CD learns a deferral function to select between expert recommendations and data-driven methods.
result L2D-CD outperforms both causal discovery methods and the expert used in isolation, identifying domains where the expert's performance is strong or weak.

GPI uses GenAI models to infer causal and predictive effects from unstructured data.

problem Estimating causal and predictive effects from unstructured data like text and images.
method Leverages open-source GenAI models to generate and represent unstructured data, applying machine learning to these representations.
result GPI efficiently estimates causal and predictive effects with quantified uncertainty, without fine-tuning.

Complex systems can be modelled at various levels of detail. Ideally, causal models of the same system should be consistent with one another in the sense that they agree in their predictions of the effects of interventions. We formalise this notion of consistency in the case of Structural Equation Models (SEMs) by intr…

2017-07-04abs ↗pdf ↗

G-Sim uses LLMs to build reliable simulators for complex systems.

problem Building robust simulators for critical domains like healthcare and logistics is challenging.
method Hybrid framework combining LLM-driven structural design and empirical calibration.
result G-Sim produces reliable, causally-informed simulators that handle non-differentiable and stochastic simulators.