Enoch H. Kang
Best AI papers explained
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
Be sure to visit the podcast's website and support the creator: podcasters.spotify.com
Author
Enoch H. Kang
Category
Podcast website
Latest episode
Nov 19, 2026
Where to listen?
Podcasts in the app Replaio Radio Coming soonPodcasts are coming to the app soon. Install now and be the first to see a whole new take on podcasts
Episodes
In-Context Parametric Inference: Point or Distribution Estimators? 15.05.2025 11:52
This paper presents an academic paper exploring the difference between Bayesian and frequentist statistical approaches within the context of deep learning . The paper compares point estimation and distribution estimation methods, specifically focusing on how they perform when used with in-context learners , which are trained to make these estimations based on observed data. The authors conduct exp...
Enough Coin Flips Can Make LLMs Act Bayesian 15.05.2025 12:56
This paper investigates whether Large Language Models (LLMs) utilize in-context learning (ICL) to perform reasoning consistent with a Bayesian framework . By using a simplified setting of biased coin flips and dice rolls, the authors analyze how LLMs update their internal probabilities based on provided examples. They find that LLMs often start with inherent biases (miscalibrated priors) but demon...
Bayesian Scaling Laws for In-Context Learning 15.05.2025 17:15
This academic paper investigates whether in-context learning (ICL) in large language models (LLMs) functions like a Bayesian learner , aiming to explain why performance increases with more examples. The authors propose and derive novel Bayesian scaling laws that model the relationship between the number of in-context examples and prediction accuracy. Through experiments on synthetic data with toy...
Posterior Mean Matching Generative Modeling 15.05.2025 18:33
This paper introduces Posterior Mean Matching (PMM) , a novel generative modeling technique rooted in Bayesian inference. Unlike traditional diffusion models, PMM employs conjugate pairs of distributions to flexibly model diverse data types such as images and text. The core mechanism involves iteratively refining noisy data approximations through online Bayesian inference updates , with the conver...
Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective 15.05.2025 22:21
This work explores evaluating when a Conditional Generative Model (CGM) is suitable for an in-context learning (ICL) task. It introduces the concept of the generative predictive p-value , extending Bayesian model criticism techniques like posterior predictive checks (PPCs) to contemporary CGMs by generating simulated data to approximate sampling from a Bayesian model. This approach allows for asse...
Dynamic Search for Inference-Time Alignment in Diffusion Models 15.05.2025 14:27
This paper highlights the challenge of aligning diffusion models with desired outcomes by optimizing reward functions , especially when gradient information is unavailable. The core contribution is the proposal of DSearch , a novel gradient-free method that reframes this alignment as a search problem on a dynamically constructed tree representing the diffusion process. DSearch utilizes heuristic f...
Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective 12.05.2025 16:06
This academic paper explores whether the in-context learning (ICL) process in Large Language Models (LLMs) behaves like Bayesian inference . The authors use the martingale property , a key characteristic of Bayesian systems with exchangeable data, as a framework for their analysis. They demonstrate that violations of this property and deviations in how LLMs' uncertainty scales with mor...
Leaked Claude Sonnet 3.7 System Instruction tuning 12.05.2025 14:03
We review leaked Claude Sonnet 3.7 System Instructions, outlining guidelines for citing information obtained from tools like web search and internal document searches, emphasizing the use of antml:cite tags for specific claims. It also describes the criteria and formats for creating "artifacts," such as code, documents, and visualizations, for collaborative content creation, includin...
Converging Predictions with Shared Information 11.05.2025 9:56
We describe a concept from a paper by Blackwell and Dubins concerning the merging of opinions or probability predictions between two individuals, Alex and Ben, as they observe increasing amounts of shared information . The central idea is that if their predictive models are updateable based on new evidence and they agree on what events are absolutely impossible , their predictions for future...
Test-Time Alignment Via Hypothesis Reweighting 11.05.2025 21:26
This paper presents HYRE , a method for quickly adapting large pretrained models to underspecified tasks like personalization or handling distribution shifts. It works by first training a single neural network that represents an ensemble of diverse models. At test time, using a small set of labeled examples from the target distribution, HYRE dynamically reweights the ensemble members based on...
Rethinking Diverse Human Preference Learning through Principal Component Analysis 11.05.2025 17:25
This paper introduces Decomposed Reward Models (DRMs) , a novel method for understanding and aligning large language models with the diverse nature of human preferences. Instead of relying on a single reward score, DRMs represent preferences as vectors and utilize Principal Component Analysis (PCA) to identify distinct directional preference components from readily available binary comparison...
Active Statistical Inference 10.05.2025 15:59
Thiis paper introduces Active Statistical Inference , a novel approach for statistical inference that strategically utilizes a machine learning model to guide data collection under a labeling budget . By prioritizing the labeling of data points where the model is uncertain, this method aims to achieve more powerful inferences and smaller confidence intervals compared to traditional met...
Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework 10.05.2025 13:21
This paper proposes a new method for optimizing the data mixtures used to train large language models (LLMs) . Traditional approaches often rely on costly trial and error or deterministic extrapolations that don't account for uncertainty, limiting their effectiveness and transferability. The authors introduce a multi-fidelity multi-scale Bayesian optimization framework , treating data curati...
AI-Powered Bayesian Inference 10.05.2025 17:55
This document introduces a novel Bayesian statistical inference method that leverages Generative Artificial Intelligence (GAI) predictions . Instead of relying solely on limited observed data or traditional statistical models, the authors propose using GAI to create synthetic data , which then informs a non-parametric prior distribution within a Bayesian framework. This approach, termed AI-...
Can Unconfident LLM Annotations Be Used for Confident Conclusions? 09.05.2025 21:09
This document presents a new method called CONFIDENCE-DRIVEN INFERENCE designed to improve the efficiency and accuracy of data annotation for tasks commonly found in computational social science . The core idea is to strategically combine large language model (LLM) annotations with a limited number of human annotations , guided by the LLM's expressed confidence levels . By prioritizing...
Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI 09.05.2025 19:42
This paper explores a new method for statistical inference in the age of AI, focusing on how predictions from large pre-trained models can serve as efficient surrogates for costly or difficult-to-obtain outcomes . Drawing a connection to the established field of surrogate outcome models in biostatistics and economics, the authors propose recalibrated prediction-powered inference (RePPI) . RePP...
Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control 09.05.2025 15:32
This paper presents the Learn then Test (LTT) framework, a novel approach for calibrating machine learning models to provide explicit statistical guarantees on their predictions. The method works with any underlying model and data distribution without requiring retraining. LTT reframes the problem of controlling statistical errors, such as false discovery rate, intersection-over-union, and ty...
How to Evaluate Reward Models for RLHF 09.05.2025 14:32
This paper introduces Preference Proxy Evaluations (PPE) , a novel benchmark designed to evaluate reward models for Reinforcement Learning from Human Feedback (RLHF) in large language models (LLMs). Unlike expensive end-to-end RLHF training, PPE utilizes proxy tasks to predict downstream LLM performance. These tasks include analyzing human preferences from a large dataset and assessing ve...
LLMs as Judges: Survey of Evaluation Methods 09.05.2025 26:56
This survey explores the increasing use of Large Language Models (LLMs) as evaluators, termed "LLMs-as-judges," across various fields due to their effectiveness and adaptability. It examines this paradigm from multiple angles, including their functionality (why they are used), methodology (how to implement them, such as single or multi-LLM systems and human-AI collaboration), appl...
The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs 09.05.2025 15:38
This paper proposes the Alternative Annotator Test (alt-test) , a novel statistical method for determining if a Large Language Model (LLM) can reliably substitute for human annotators in research tasks across various fields. The test involves comparing LLM annotations to those of a small group of human annotators on a subset of data to see if the LLM aligns better with the group than individual...
Limits to scalable evaluation at the frontier: LLM as Judge won’t beat twice the data 09.05.2025 12:15
This paper examines the limitations of using large language models (LLMs) as judges for evaluating other models, particularly at the "evaluation frontier" where new models may be better than the judge. While using LLMs as judges is a promising approach for scalable evaluation due to the cost and bottleneck of human annotation, this method introduces biases that can distort model ranki...
Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation 09.05.2025 13:23
This paper introduces Stratified Prediction-Powered Inference (StratPPI) , a new method for improving the statistical evaluation of models , particularly Large Language Models (LLMs), which often face costly human annotation bottlenecks. Building on Prediction-Powered Inference (PPI) , which combines small amounts of human-labeled data with larger, potentially biased automatic data, StratPPI ut...
Accelerating Unbiased LLM Evaluation via Synthetic Feedback 09.05.2025 20:45
This paper proposes Control Variates Evaluation , a method for efficiently evaluating large language models (LLMs) that reduces reliance on expensive human annotations . While synthetic feedback from other LLMs is cheaper, it introduces bias . This new approach combines human and synthetic feedback to achieve unbiased win-rate calculations with significantly fewer human annotations . Exp...
Prediction-Powered Statistical Inference Framework 09.05.2025 10:47
This paper presents "Prediction-Powered Inference," a novel framework for conducting statistical inference while integrating predictions from machine learning systems with experimental data. The authors, including Anastasios N. Angelopoulos, Stephen Bates, Clara Fannjiang, Michael I. Jordan, and Tijana Zrnic, propose algorithms that calculate provably valid confidence intervals f...
Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL 09.05.2025 15:32
This paper presents Gradient Variance Minimization (GVM) , a novel technique for optimizing Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs). The core idea is to dynamically allocate computational resources (sampling budget) across prompts based on their difficulty and gradient norms, aiming to minimize the variance of the stochastic gradient estimation. Unlike traditional met...
Similar podcasts
Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.