CrystalCandle creates user-friendly explanations for machine learning models.
problem Low trust in predictive models due to lack of interpretability.
method End-to-end pipeline for model interpretation, including Model Importer, Interpreter, Narrative Generator, and Exporter.
result CrystalCandle leads to higher adoption rates and improved downstream metrics.
LLMs can help explain credit risk models but not autonomously.
problem Leveraging LLMs for post-hoc explainability in credit risk models.
method Comparison of LLM outputs with SHAP and coefficient-based attributions on three LMs.
result LLMs reliably preserve feature-importance rankings but poorly align with autonomous explanations.
The paper argues for prioritizing identifying structure over complex models for scientific discovery.
problem Underdetermination of mechanisms in high-dimensional data, leading to unreliable explanations.
method Proposes concrete standards for 'mechanistic ML' to avoid collapsing explanations.
result Large language models (LLMs) can collapse large equivalence classes of explanations, making it hard to distinguish between mechanisms.
Study finds strong link between crypto narratives and prices.
problem Understanding the impact of crypto narratives on prices.
method Topic modeling of Twitter data combined with sentiment analysis.
result Strong correlation between narratives and crypto prices.
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.
Automated prediction of valence, one key feature of a person's emotional state, from individuals' personal narratives may provide crucial information for mental healthcare (e.g. early diagnosis of mental diseases, supervision of disease course, etc.). In the Interspeech 2018 ComParE Self-Assessed Affect challenge, the …
Improved earnings predictions through text-morphed earnings calls.
problem Improving earnings prediction models using narrative information.
method Introducing a text-morphing methodology to generate counterfactual transcripts.
result Analysts over-react to sentiment and under-react to risk and uncertainty.
Algorithm improves SLR efficiency in financial narratives.
problem Fragmented understanding of financial narratives.
method NLP, clustering, interpretability tools.
result Unified narrative modeling approaches needed.
A new platform models how narratives influence financial markets.
problem Explaining irrational market behaviors through narratives.
method Integrated opinion dynamics and agent-based modeling.
result Initial results show how narratives shape financial outcomes.
Automatic understanding of domain specific texts in order to extract useful relationships for later use is a non-trivial task. One such relationship would be between railroad accidents' causes and their correspondent descriptions in reports. From 2001 to 2016 rail accidents in the U.S. cost more than $4.6B. Railroads i…
AI helps in drug discovery with understandable explanations.
problem Understanding the complex models behind AI-generated drugs.
method Explainable AI methods to interpret deep learning models.
result Improved interpretability of AI-generated drug properties.
Paper analyzes systematic jump risk around the clock using news narratives.
problem Identifying and managing priced risks in real-time market conditions.
method Combining high-frequency market data with news narratives classified by an LLM.
result Significant heterogeneity in risk premia, with macroeconomic news commanding the largest premium.
Study finds whitepaper narratives do not predict market factor structure.
problem Predicting market behavior from cryptocurrency whitepaper claims.
method Zero-shot NLP classification combined with CP tensor decomposition of market data.
result Weak alignment between whitepaper claims and market statistics and latent factors.
Detects systematic anomalies in consumer complaints using NLP.
problem Detecting small, frequent anomalies in consumer complaints.
method NLP conversion of narratives, followed by anomaly detection algorithm.
result Demonstrates effectiveness of NLP for detecting systematic anomalies.
Study detects SLI in children from spontaneous narrative transcripts.
problem Detecting Specific Language Impairment (SLI) in children.
method Three-stage pipeline: feature extraction, dimensionality reduction, and classification.
result 97.13% accuracy in identifying SLI from transcripts.
This paper presents the contemporary Fundamental Theorem of Asset Pricing as being equivalent to approaches to pricing that emerged before 1700 in the context of Virtue Ethics. This is done by considering the history of science and mathematics in the thirteenth and seventeenth century. An explanation as to why these ap…
Narrative disclosures in 10-K filings improve bankruptcy prediction beyond accounting ratios.
problem Traditional bankruptcy prediction models rely on accounting ratios, which may not capture early warning signals.
method Developed a PB Stress Score based on distress-specific language in 10-K narratives, evaluated against accounting and dictionary benchmarks.
result Adding the PB Stress Score increases AUC from 0.8323 to 0.9019 and improves top-decile bankruptcy capture from 44.12% to 64.71%.
Analyst reports contain valuable information for investment decisions.
problem Investment value in analyst reports is not fully understood or utilized.
method Embedded analyst reports with LLMs and ML forecasts of future returns.
result Portfolios formed on analyst report narratives outperform numerical forecasts and established factors.
Unified theory of deep learning from approximation to emergence.
problem Understanding the mechanisms behind deep learning.
method Unified, proof-oriented approach tracing from classical foundations to contemporary mechanisms.
result Unified theory explaining deep learning from approximation to emergence.
Study shows GPT's earnings forecasts are human-like but not always accurate.
problem Information friction in AI-generated financial analysis.
method Examined GPT's earnings forecasts following corporate earnings releases and proposed a diagnostic framework.
result GPT's narrative attention is consistent and human-like but not always associated with higher forecast accuracy.
Attention mechanisms in deep neural networks have achieved excellent performance on sequence-prediction tasks. Here, we show that these recently-proposed attention-based mechanisms---in particular, the Transformer with its parallelizable self-attention layers, and the Memory Fusion Network with attention across modalit…
In this paper we present an early Apprenticeship Learning approach to mimic the behaviour of different players in a short adaption of the interactive fiction Anchorhead. Our motivation is the need to understand and simulate player behaviour to create systems to aid the design and personalisation of Interactive Narrativ…
FinCausal 2020 task detects financial document causality.
problem Detect causal relationships in financial documents.
method Binary classification and relation extraction tasks.
result 16 teams participated, 13 submitted system descriptions.
Developing an AI economist agent using RAG, knowledge graphs, and LLMs for economic scenario analysis.
problem Economic scenario analysis using large language models and knowledge graphs.
method Proposing an RAG-based AI economist framework that utilizes knowledge graphs and LLMs.
result Improves economic coherence and traceability in generated reports.
Analyzes news graphs to predict financial market dislocations.
problem Predicting financial market dislocations using news content.
method Extracts entities from news articles, aggregates them into graphs, applies network analysis, and uses sentiment analysis.
result Identifies high entropy in news graphs correlates with financial market dislocations.
A text mining approach is proposed based on latent Dirichlet allocation (LDA) to analyze the Consumer Financial Protection Bureau (CFPB) consumer complaints. The proposed approach aims to extract latent topics in the CFPB complaint narratives, and explores their associated trends over time. The time trends will then be…
Paper develops a method for valid inference using language model predictions from verbal autopsy narratives.
problem Valid inference from verbal autopsy narratives for public health decision-making.
method Develops multiPPI++ method for valid inference using NLP techniques for COD prediction.
result Demonstrates the effectiveness of multiPPI++ in handling transportability issues and recovering ground truth estimates.
We present a new recurrent neural network topology to enhance state-of-the-art machine learning systems by incorporating a broader context. Our approach overcomes recent limitations with extended narratives through a multi-layered computational approach to generate an abstract context representation. Therefore, the dev…
LLMs outperform human analysts in predicting earnings direction.
problem Evaluating financial statements without narrative or industry-specific information.
method Trained GPT4 on standardized, anonymous financial statements and instructed to predict earnings direction.
result LLMs predict earnings directionally with accuracy comparable to narrowly trained ML models.
Many methods to explain black-box models, whether local or global, are additive. In this paper, we study global additive explanations for non-additive models, focusing on four explanation methods: partial dependence, Shapley explanations adapted to a global setting, distilled additive explanations, and gradient-based e…
Framework detects influential actors in disinformation networks.
problem Identifying and countering hostile influence operations on social media.
method Combines NLP, ML, graph analytics, and causal inference.
result 96% precision, 79% recall, 96% PR-curve area for IO detection.
AXE evaluates explanations to avoid misleading Rashomon set model selection.
problem Evaluating explanations for Rashomon set models to avoid false selection.
method Proposed AXE method to evaluate explanation quality.
result AXE detects adversarial fairwashing with 100% success rate.
The paper proposes criteria and methods for evaluating and aggregating feature-based model explanations.
problem Lack of quantitative evaluation criteria for feature-based model explanations.
method Developed quantitative evaluation criteria (low sensitivity, high faithfulness, low complexity), devised a framework for aggregation, and derived a new aggregate Shapley value explanation function.
result A new aggregate Shapley value explanation function that minimizes sensitivity.
New definition reveals encoding explanations that retain predictive power.
problem Challenges in evaluating and identifying encoding explanations.
method Developed a definition of encoding based on conditional dependence.
result Existing evaluation scores do not rank non-encoding explanations correctly, but STRIPE-X does.
GRANITE unifies feature-based explanation methods to reduce disagreement.
problem Disagreement among feature-based explanation methods.
method GRANITE partitions feature space into regions minimizing interaction and distribution influences.
result Unified and consistent feature explanations.
Differentially private algorithms protect model explanations from leaking training data.
problem Model explanations can leak training data, compromising privacy.
method Adaptive differentially private gradient descent algorithm to produce accurate, private explanations.
result Privacy amplification and reduction of overall privacy loss on explanation data.
We consider objective evaluation measures of saliency explanations for complex black-box machine learning models. We propose simple robust variants of two notions that have been considered in recent literature: (in)fidelity, and sensitivity. We analyze optimal explanations with respect to both these measures, and while…
Improves global counterfactual explanations for model recourse.
problem Inability to provide explanations beyond local instances.
method Investigates and improves Actionable Recourse Summaries (AReS) for global counterfactual explanations.
result Develops more efficient and interactive explainability tools.
New framework evaluates model explanations based on decision task improvement.
problem Evaluation of model explanations often misses practical value.
method Decision-theoretic framework quantifying three key values.
result Provides benchmarks and interprets human-AI decision support.
We define and compute plausible counterfactual explanations using density constraints.
problem Efficiently compute plausible counterfactual explanations for machine learning models.
method Propose and study a formal definition of plausible counterfactual explanations, use density estimators, and introduce convex density constraints.
result Convex density constraints ensure plausible and feasible counterfactual explanations.
G-SHAP generates multiple types of explanations for machine learning models.
problem Understanding model predictions and their differences across groups.
method Generalization of SHAP method to produce additional types of explanations.
result G-SHAP produces explanations for classification, intergroup differences, and model failure.
LLMs' explanations are often insufficient and vary with input distribution.
problem Evaluating the sufficiency of LLM explanations without predefined biases.
method Generalizing sufficiency to arbitrary explanations, using LLM's input beliefs, and introducing SCSuff metric.
result Explanation sufficiency can vary with input distribution and is weakly correlated with model size, accuracy, or output entropy.
Study finds visual explanations do not significantly improve human accuracy or trust in model predictions.
problem Measuring the impact of visual explanations on human accuracy and trust in model predictions.
method Randomized controlled trial with image-based age prediction task, varying levels of explanation quality.
result Visual explanations do not significantly alter human accuracy or trust in the model.
Despite a growing literature on explaining neural networks, no consensus has been reached on how to explain a neural network decision or how to evaluate an explanation. Our contributions in this paper are twofold. First, we investigate schemes to combine explanation methods and reduce model uncertainty to obtain a sing…
Many proposed methods for explaining machine learning predictions are in fact challenging to understand for nontechnical consumers. This paper builds upon an alternative consumer-driven approach called TED that asks for explanations to be provided in training data, along with target labels. Using semi-synthetic data fr…
Managing large-scale transportation infrastructure projects is difficult due to frequent misinformation about the costs which results in large cost overruns that often threaten the overall project viability. This paper investigates the explanations for cost overruns that are given in the literature. Overall, four categ…
This research investigates reliable local explanations for machine listening models.
problem Generating reliable local explanations for machine listening models.
method Investigates the sensitivity of SoundLIME explanations to input perturbations and proposes a novel method for identifying suitable content types.
result SoundLIME explanations are sensitive to the content in occluded input regions, and the average magnitude of input mel-spectrogram bins is the most suitable content type for temporal explanations.
Defines explanations for classifier outcomes using causal concepts.
problem Understanding classifier outcomes in a causal context.
method Proposes a new definition of explanation based on causality, compares it with existing notions, and evaluates it experimentally.
result Experimental evaluation shows the new definition's effectiveness on financial datasets.