Search Results for author:
Found 43 papers, 14 papers with code
Assessing Economic Viability: A Comparative Analysis of Total Cost of Ownership for Domain-Adapted Large Language Models versus State-of-the-art Counterparts in Chip Design Coding Assistance
This paper presents a comparative analysis of total cost of ownership (TCO) and performance between domain-adapted large language models (LLM) and state-of-the-art (SoTA) LLMs , with a particular emphasis on tasks related to coding assistance for chip design.
Multiple Instance Learning for Glioma Diagnosis using Hematoxylin and Eosin Whole Slide Images: An Indian Cohort Study
It establishes new performance benchmarks in glioma subtype classification across multiple datasets, including a novel dataset focused on the Indian demographic (IPD- Brain), providing a valuable resource for existing research.
NICE: To Optimize In-Context Examples or Not?
Recent work shows that in-context learning and optimization of in-context examples (ICE) can significantly improve the accuracy of large language models (LLMs) on a wide range of tasks, leading to an apparent consensus that ICE optimization is crucial for better performance.
Pre-registration for Predictive Modeling
Amid rising concerns of reproducibility and generalizability in predictive modeling, we explore the possibility and potential benefits of introducing pre-registration to the field.
GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval
Given a query and a document corpus, the information retrieval (IR) task is to output a ranked list of relevant documents.
Causal Inference Using LLM-Guided Discovery
At the core of causal inference lies the challenge of determining reliable causal graphs solely based on observational data.
Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals
We hence present a second approach based on matching, and propose a method that is guided by an LLM at training-time and learns a dedicated embedding space.
Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost
Instead, we propose a sampling strategy based on the difference in prediction scores between the base model and the finetuned NLP model, utilizing the fact that most NLP models are finetuned from a base model.
Causal Effect Regularization: Automated Detection and Removal of Spurious Attributes
We prove that our method only requires that the ranking of estimated causal effects is correct across attributes to select the correct classifier.
On Counterfactual Data Augmentation Under Confounding
Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data.
Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers
Therefore, using methods from the causal inference literature, we propose an algorithm to regularize the learnt effect of the features on the model's prediction to the estimated effect of feature on label.
Causal Reasoning and Large Language Models: Opening a New Frontier for Causality
The causal capabilities of large language models (LLMs) is a matter of significant debate, with critical implications for the use of LLMs in societally impactful domains such as medicine, science, law, and policy.
Counterfactual Generation Under Confounding
Given a causal generative process, we formally characterize the adverse effects of confounding on any downstream tasks and show that the correlation between generative factors (attributes) can be used to quantitatively measure confounding between generative factors.
Using Interventions to Improve Out-of-Distribution Generalization of Text-Matching Recommendation Systems
To explain this generalization failure, we consider an intervention-based importance metric, which shows that a fine-tuned model captures spurious correlations and fails to learn the causal features that determine the relevance between any two text inputs.
The Counterfactual-Shapley Value: Attributing Change in System Metrics
Specifically, we propose a method to estimate counterfactuals using time-series predictive models and construct an attribution score, CF-Shapley, that is consistent with desirable axioms for attributing an observed change in the output metric.
Probing Classifiers are Unreliable for Concept Removal and Detection
Even under the most favorable conditions for learning a probing classifier when a concept's relevant features in representation space alone can provide 100% accuracy, we prove that a probing classifier is likely to use non-concept features and thus post-hoc or adversarial methods will fail to remove the concept correctly.
Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization
Based on the relationship between spurious attributes and the classification label, we obtain realizations of the canonical causal graph that characterize common distribution shifts and show that each shift entails different independence constraints over observed variables.
Machine Explanations and Human Understanding
Our key result is that without assumptions about task-specific intuitions, explanations may potentially improve human understanding of model decision boundary, but they cannot improve human understanding of task decision boundary or model error.
Deep End-to-end Causal Inference
Causal inference is essential for data-driven decision making across domains such as business engagement, medical treatment and policy making.
Long Story Short: Omitted Variable Bias in Causal Machine Learning
Therefore, simple plausibility judgments on the maximum explanatory power of omitted variables (in explaining treatment and outcome variation) are sufficient to place overall bounds on the size of the bias.
Matching Learned Causal Effects of Neural Networks with Domain Priors
A trained neural network can be interpreted as a structural causal model (SCM) that provides the effect of changing input variables on the model's output.
Sayer: Using Implicit Feedback to Optimize System Policies
We develop a methodology, called Sayer, that leverages implicit feedback to evaluate and train new system policies.
The Connection between Out-of-Distribution Generalization and Privacy of ML Models
Through extensive evaluation on a synthetic dataset and image datasets like MNIST, Fashion-MNIST, and Chest X-rays, we show that a lower OOD generalization gap does not imply better robustness to MI attacks.
DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions
Estimation of causal effects involves crucial assumptions about the data-generating process, such as directionality of effect, presence of instrumental variables or mediators, and whether all relevant confounders are observed.
Noise2Fast: Fast Self-Supervised Single Image Blind Denoising
Recent approaches have allowed for the denoising of single noisy images without access to any training data aside from that very image.
Causally Constrained Data Synthesis for Private Data Release
However for real-world applications, the privacy of data is critical.
On Cofibrations of Permutative categories
In this note we introduce a notion of free cofibrations of permutative categories.
Category Theory Algebraic Topology
Technology Readiness Levels for Machine Learning Systems
The development and deployment of machine learning (ML) systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end.
The Importance of Modeling Data Missingness in Algorithmic Fairness: A Causal Perspective
For example, in multi-stage settings where decisions are made in multiple screening rounds, we use our framework to derive the minimal distributions required to design a fair algorithm.
Split-Treatment Analysis to Rank Heterogeneous Causal Effects for Prospective Interventions
For many kinds of interventions, such as a new advertisement, marketing intervention, or feature recommendation, it is important to target a specific subset of people for maximizing its benefits at minimum cost or potential harm.
Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End
In addition, by restricting the features that can be modified for generating counterfactual examples, we find that the top-k features from LIME or SHAP are often neither necessary nor sufficient explanations of a model's prediction.
DoWhy: An End-to-End Library for Causal Inference
In addition to efficient statistical estimators of a treatment's effect, successful application of causal inference requires specifying assumptions about the mechanisms underlying observed data and testing whether they are valid, and to what extent.
Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals
We present a method for generating counterfactuals by incorporating a structural causal model (SCM) in an improved variant of Adversarially Learned Inference (ALI), that generates counterfactuals in accordance with the causal relationships between attributes of an image.
Domain Generalization using Causal Matching
In the domain generalization literature, a common objective is to learn representations independent of the domain after conditioning on the class label.
Ranked #1 on
Domain Generalization
on Rotated Fashion-MNIST
Learnings from Technological Interventions in a Low Resource Language: A Case-Study on Gondi
The primary obstacle to developing technologies for low-resource languages is the lack of usable data.
Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
For explanations of ML models in critical domains such as healthcare and finance, counterfactual examples are useful for an end-user only to the extent that perturbation of feature inputs is feasible in the real world.
Alleviating Privacy Attacks via Causal Learning
Such privacy risks are exacerbated when a model's predictions are used on an unseen data distribution.
Quantifying Infra-Marginality and Its Trade-off with Group Fairness
To quantify this bias, we propose a general notion of $\eta$-infra-marginality that can be used to evaluate the extent of this bias.
Quantifying Error in the Presence of Confounders for Causal Inference
We show that many popular methods, including back-door methods can be considered as weighting or representation learning algorithms, and provide general error bounds for their causal estimates.
Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions.
Learning to Prescribe Interventions for Tuberculosis Patients Using Digital Adherence Data
Digital Adherence Technologies (DATs) are an increasingly popular method for verifying patient adherence to many medications.
Split-door criterion: Identification of causal effects through auxiliary outcomes
We present a method for estimating causal effects in time series data when fine-grained information about the outcome of interest is available.
Algorithms for Generating Ordered Solutions for Explicit AND/OR Structures
The proposed algorithms use a best first search technique and report the solutions using an implicit representation ordered by cost.
