Medium

Aparna Dhinakaran

In

Data Science Collective

by

Aparna Dhinakaran

·

Oct 8, 2025

Should I Use the Same Model for My Eval as My Agent?

Examining Self-Evaluation Bias of Major LLMs

Should I Use the Same Model for My Eval as My Agent?

In

Data Science Collective

by

Aparna Dhinakaran

·

Aug 20, 2025

LLM-as-a-Judge: When to Use Reasoning, CoT, and Explanations

A guide on what to use where — and why

LLM-as-a-Judge: When to Use Reasoning, CoT, and Explanations

In

Arize AI

by

Aparna Dhinakaran

·

Aug 1, 2025

What Is Prompt Learning?

Prompts, like models, should improve with feedback — not stay static.

What Is Prompt Learning?

In

TDS Archive

by

Aparna Dhinakaran

·

Sep 21, 2024

Choosing Between LLM Agent Frameworks

The tradeoffs between building bespoke code-based agents and the major agent frameworks.

Choosing Between LLM Agent Frameworks

In

TDS Archive

by

Aparna Dhinakaran

·

Aug 30, 2024

Navigating the New Types of LLM Agents and Architectures

The failure of ReAct agents gives way to a new generation of agents — and possibilities

Navigating the New Types of LLM Agents and Architectures

In

TDS Archive

by

Aparna Dhinakaran

·

Jul 31, 2024

Evaluating SQL Generation with LLM as a Judge

Results point to a promising approach

Evaluating SQL Generation with LLM as a Judge

In

TDS Archive

by

Aparna Dhinakaran

·

May 1, 2024

Large Language Model Performance in Time Series Analysis

How do major LLMs stack up at detecting anomalies or movements in the data when given a large set of time series data within the context…

Large Language Model Performance in Time Series Analysis

In

TDS Archive

by

Aparna Dhinakaran

·

Apr 6, 2024

Tips for Getting the Generation Part Right in Retrieval Augmented Generation

Results from experiments to evaluate and compare GPT-4, Claude 2.1, and Claude 3.0 Opus

Tips for Getting the Generation Part Right in Retrieval Augmented Generation

In

TDS Archive

by

Aparna Dhinakaran

·

Mar 26, 2024

Model Evaluations Versus Task Evaluations

Understanding the difference for LLM applications

Model Evaluations Versus Task Evaluations

In

TDS Archive

by

Aparna Dhinakaran

·

Mar 8, 2024

Why You Should Not Use Numeric Evals For LLM As a Judge

Testing major LLMs on how well they conduct numeric evaluations

Why You Should Not Use Numeric Evals For LLM As a Judge

Aparna Dhinakaran

Aparna Dhinakaran

Co-Founder and CPO of Arize AI. Formerly Computer Vision PhD at Cornell, Uber Machine Learning, UC Berkeley AI Research.

Following

Help

Status

About

Careers

Press

Blog

Store

Privacy

Rules

Terms

Text to speech