SLED improves factuality in LLMs without external knowledge.
problem Unreliable or factually incorrect outputs from large language models.
method Contrasts final layer logits with early layers' logits, uses approximate gradient to refine outputs.
result Consistently improves factual accuracy over existing methods.
Transformers can store facts efficiently using associative memories.
problem Understanding how transformers store and recall factual information.
method Proved linear scaling of storage capacities for linear and MLP associative memories, introduced a synthetic task, and analyzed gradient flow.
result Shallow transformers can achieve near optimal storage capacity for factual recall tasks using associative memories.
New methods for explaining Random Forest predictions using case-based reasoning.
problem Lack of explainability for black-box machine learning models like Random Forests.
method Extracting distance metric from Random Forests to identify prototypes, critics, counter-factuals, and semi-factuals.
result Identified special points from training datasets to explain Random Forest predictions.
FactTest assesses LLM factuality with Type I error control.
problem Lack of rigorous factuality verification for LLMs.
method Formulates factuality testing as hypothesis testing, ensuring Type I and II error control.
result Improves model accuracy by over 40% in abstaining from unknown questions.
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.
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.
MACI improves LLM factuality inference with higher retention and lower time cost.
problem Ensuring factuality in LLM responses for high-stakes domains.
method Reformulated conformal inference in a multiplicative filtering setting, leveraging ensembles for more accurate factuality scores and group-conditional calibration.
result MACI achieves higher retention and lower time cost compared to baselines, preserving validity through group-conditional calibration.
Study predicts factuality and bias of news media sources.
problem Characterizing the factuality and bias of news media sources.
method Used a large list of news websites and features from articles, Wikipedia pages, Twitter accounts, URL structure, and web traffic.
result Significant performance gains over baselines, confirming the importance of various features.
Paper addresses shortcomings in pointer generator networks for summarization.
problem Extractive summaries and factual inaccuracies in generated text.
method Appends traditional linguistic information to teach networks on text structure.
result Feasibility and potential of additional cues for improved generation.
Proposes a deep learning framework for estimating counterfactual outcomes.
problem Challenges in estimating individual outcomes under different treatments.
method Deep variational Bayesian framework integrating factual and similar subjects' outcomes.
result Rigorously integrates individual features and similar subjects' responses for counterfactual outcomes.
Develops a method for constructing KBs with tunable precision for subjective and factual attributes.
problem Complexity in measuring subjective attributes complicates precision estimation in KBs.
method Probabilistically models user consensus with respect to each entity-attribute pair, using neural networks to fit the model.
result Learned models can successfully control KB's precision and outperform baselines in attribute prediction.
MGM improves media profiling by integrating textual and structural features.
problem Evaluating the bias and factuality of news media from digital data.
method MediaGraphMind (MGM) framework using variational EM, integrating textual and structural features.
result Achieves new state-of-the-art results in media profiling.
HabitatAgent offers a multi-agent system for transparent housing consultation.
problem Opaque reasoning and brittle multi-constraint handling in housing recommendation systems.
method HabitatAgent is a multi-agent architecture with specialized roles for memory, retrieval, generation, and validation.
result HabitatAgent achieves 95% accuracy in real user consultation scenarios, significantly outperforming a strong baseline.
PO-Flow models potential and counterfactual outcomes for personalized treatment decisions.
problem Predicting individualized treatment effects from observational data.
method Continuous normalizing flow (CNF) framework for causal inference.
result Unified approach to potential outcome prediction, treatment effect estimation, and counterfactual prediction.
New findings show tool-augmented models can recall unlimited facts, outperforming purely memorized models.
problem Limitations of purely memorized models in recalling large amounts of factual information.
method Demonstrated the benefits of in-tool learning (external retrieval) over in-weight learning (memorization) for factual recall.
result Proved that tool-use enables unbounded factual recall via a simple and efficient circuit construction.
Bounds on factual and counterfactual distributions under measurement error in discrete models.
problem Measurement errors in discrete data and their impact on inference.
method Expressing modeling assumptions as linear constraints and using linear programming to derive bounds.
result Sharp bounds on factual and counterfactual distributions for various models, including instrumental variable scenarios.
Estimates counterfactual outcomes linking observed and unobserved data.
problem Estimating expected counterfactual outcomes for individuals.
method Introduces retrospective counterfactual estimators and prediction intervals linking observed and unobserved outcomes.
result Retrospective counterfactual estimators and prediction intervals asymptotically satisfy valid coverage under standard causal assumptions.
This study quantifies uncertainty in comparing treatments using RCTs with before-and-after measures.
problem Uncertainty in comparing treatments using RCTs with before-and-after measures.
method New statistical modeling principle called ETZ enables counterfactual uncertainty quantification (CUQ) in RCTs with Before-and-After Repeated Measures.
result CUQ typically has lower variability than factual uncertainty quantification and can be achieved in RCTs.
We investigate the problem of estimating the causal effect of a treatment on individual subjects from observational data, this is a central problem in various application domains, including healthcare, social sciences, and online advertising. Within the Neyman Rubin potential outcomes model, we use the Kullback Leibler…
Task focuses on fact checking in Q&A forums, improving over baseline systems.
problem Fact checking in community Q&A forums to distinguish factual from opinion.
method Two subtasks: distinguishing factual vs. opinion/advice/socializing, predicting answer truthfulness.
result Improved over baseline systems for both subtasks, but not for Subtask B.
Benchmark evaluates AI-generated financial QA hallucinations, highlighting system vulnerabilities.
problem Ensuring factual accuracy of AI-generated financial QA outputs.
method Developed a benchmark dataset and evaluated six detection methods under clean and noisy conditions.
result LLM-based judges and embedding methods perform best, but degrade under noisy conditions.
Data selection boosts fact memorization in language models.
problem Language models struggle to accurately memorize factual knowledge.
method Formalizes fact memorization, proposes data selection schemes based on training loss.
result Data selection boosts fact accuracy to model capacity and improves performance.
Machine learning improves learning and memory retention by optimizing study sessions.
problem Improving learning and memory retention methods for factual material.
method Large-scale randomized controlled trial with machine learning optimization of study sessions.
result Study sessions optimized with machine learning lead to 67% longer retention and 50% higher return rate.
We create a large dataset for fact checking claims and improve prediction accuracy.
problem Fact checking claims from multiple sources is challenging.
method We created a comprehensive dataset and developed a novel method for automatic veracity prediction.
result Our model achieves a Macro F1 of 49.2%, showing significant performance improvements.
Causal inference analysis is the estimation of the effects of actions on outcomes. In the context of healthcare data this means estimating the outcome of counter-factual treatments (i.e. including treatments that were not observed) on a patient's outcome. Compared to classic machine learning methods, evaluation and val…
Sharp limits found for storing and retrieving input-output associations in linear associative memories.
problem Understanding the fundamental limits of storing and retrieving input-output associations in neural networks.
method Study of a minimal linear associative memory model, introducing a decoupled model and using statistical physics to characterize storage capacity.
result Linear associative memory can store up to 1/2 log(p) associations, providing a sharp statistical-physics characterization.
Prognosticator improves performance in non-stationary MDPs.
problem Real-world applications often violate the stationary assumption in reinforcement learning.
method A policy gradient algorithm that maximizes a forecast of future performance.
result Prognosticator outperforms online adaptation techniques in non-stationary MDPs.
CVIB uses information theory to learn counterfactuals from MNAR data without RCTs.
problem Debiasing learning from missing-not-at-random (MNAR) data in recommendation systems.
method CVIB, a variational information bottleneck, separates task-aware mutual information into factual and counterfactual parts.
result CVIB significantly enhances both shallow and deep models in recommendation systems.
Proposes a game-theoretic approach for class-dependent rationalization.
problem Optimizing feature selection for complex neural predictors.
method A game-theoretic approach where classes compete to find evidence for factual and counterfactual scenarios.
result The method identifies both factual and counterfactual rationales consistent with human rationalization.
This paper introduces DCE for better counterfactual explanations using optimal transport.
problem Lack of nuanced distributional characteristics in existing counterfactual explanations.
method Formulates a chance-constrained optimization problem using optimal transport to derive counterfactual distributions.
result DCE provides deeper insights into decision-making models by aligning counterfactual distributions with factual ones.
MetaCI uses meta-learning to generalize causal inference across heterogeneous populations.
problem Generalizing causal inference from multiple homogeneous subgroups to a heterogeneous population.
method MetaCI employs meta-learning to handle data distribution shifts and concept drifts.
result MetaCI outperforms random initialization and other methods in counterfactual inference.
LLMs compress financial texts, but distort decision-making.
problem LLMs compress financial texts, altering decision-making.
method Analyzed two diagnostic patterns: decontextualization and model dependency. Proposed Agentic Context Compression.
result LLM-compressed financial texts alter decision-making.
Transformers can be hijacked by context, but deeper models are more robust.
problem Robustness of Transformers against context hijacking for linear classification.
method Developed a theoretical analysis on the robustness of linear transformers, considering model depth, training context lengths, and number of hijacking context tokens.
result Deeper transformers are more robust to context hijacking.
A brief historical perspective is first given concerning financial crashes, - from the 17th till the 20th century. In modern times, it seems that log periodic oscillations are found before crashes in several financial indices. The same is found in sand pile avalanches on Sierpinski gaskets. A discussion pertains to the…
Language models learn automotive complaints, improving defect detection.
problem Detecting technical quality issues in customer feedback.
method Continual pre-training on ODI Complaints data set.
result Models achieve high precision in identifying technical terms.
FAKTA automates fact checking across media sources.
problem Automating fact checking across diverse media sources.
method Unified framework integrating document retrieval, stance detection, evidence extraction, and linguistic analysis.
result FAKTA predicts factuality and provides evidence for claims.
This paper enhances language models with knowledge awareness.
problem Understanding how much knowledge pretrained language models grasp.
method Inserting explicit knowledge layers into pretraining without changing transformer architecture.
result Significantly more knowledge packed into transformer parameters.
ARCHER counters bias in HER to improve sample efficiency in RL.
problem Sample inefficiency in deep RL due to biased replay buffer experiences.
method ARCHER extends HER with aggressive hindsight rewards to counter bias.
result ARCHER increases sample efficiency in RL applications with limited computing budget.
VERAFI improves financial AI by verifying calculations and compliance.
problem Financial AI systems generate errors and violations during reasoning.
method VERAFI combines dense retrieval, reranking, and automated reasoning policies.
result VERAFI achieves 94.7% factual correctness, 81% relative improvement.
Cryptos remained resilient after SVB's collapse, contrary to expectations.
problem Impact of SVB collapse on crypto markets.
method Factual summary, sentiment analysis, and market performance examination.
result Cryptocurrencies showed resilience after SVB's collapse.
Algorithm simulates counterfactuals for fairness analysis.
problem Analytical intractability of counterfactuals in conditional distributions.
method Proposes an algorithm using particle filtering for discrete and continuous variables.
result Asymptotically valid inference for counterfactuals.
Variance-Calibrated Modulation (VCM) addresses the likelihood trap in LLMs by reshaping the probability distribution before truncation.
problem LLMs fall into the likelihood trap, leading to repetitive degeneration and vocabulary dullness.
method VCM reshapes the probability distribution before truncation through Contextual Searchlight and Adaptive Self-Debiasing.
result VCM mitigates the likelihood trap across open-ended generation, factual QA, and mathematical reasoning.
Generates counterfactuals in target domain from source domain observations.
problem Cross-domain learning with domain shifts and lack of parallel datasets.
method Unsupervised, Neural Causal Models, Joint Causal Graphs, Effect-Intrinsic vs Domain-Intrinsic Variables.
result Framework generates counterfactuals that closely match ground truth.
CausalLongPFN predicts counterfactual outcomes from time-series data.
problem Predicting future outcomes under varying treatments in time-series data with confounding and heterogeneity.
method Prior-fitted network pretrained on synthetic episodes of temporal structural causal models.
result CausalLongPFN outperforms domain-trained models on factual and counterfactual prediction tasks.
RAG-IT automates financial analysis using LLMs and specialized datasets.
problem Manual financial analysis is time-consuming and requires expertise.
method Retrieval-Augmented Instruction Tuning (RAG-IT) fine-tunes an LLM for financial tasks.
result RAG-IT improves financial report generation performance compared to commercial systems.
Study evaluates five LLMs for financial report analysis, revealing performance differences and variability.
problem Lack of understanding in reliability, consistency, and transparency of LLMs in financial analysis.
method Human evaluation, automated similarity metrics, and behavioral diagnostics applied to five transformer-based LLMs over U.S. 10-K filings.
result No single LLM consistently dominates across all evaluation perspectives, highlighting variability and need for interpretability.
Linguistic calibration improves long-form text confidence.
problem LMs hallucinate, leading to suboptimal decisions.
method Defining linguistic calibration, training framework, reinforcement learning.
result Llama 2 7B is significantly more calibrated than baselines.
Ranked second in fact-checking task, using DRR NN with embeddings.
problem Fact-checking questions in community forums.
method Deeply Regularized Residual Neural Network (DRR NN) with Universal Sentence Encoder embeddings, ensemble methods.
result Ranked second in fact-checking task.