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

Technology

Podcast website

podcasters.spotify.com

Latest episode

Nov 19, 2026

Where to listen?

Podcasts in the app Replaio Radio Coming soon

Podcasts are coming to the app soon. Install now and be the first to see a whole new take on podcasts

Get it on Google Play Install for free Android 10M+ downloads · 4.7+ rating iOS soon

Episodes

LLM Populations Form Social Conventions and Collective Bias 29.05.2025

This academic article investigates the emergence of social conventions in populations of large language models (LLMs) , exploring whether these AI agents can establish shared behaviors through interaction. The research demonstrates that LLM populations spontaneously develop these conventions, similar to human groups, and that collective biases can arise during this process, even without individual...

LLM Generated Persona is a Promise with a Catch 29.05.2025

This paper examines the potential and significant challenges of using large language models (LLMs) to create realistic digital personas for simulating human behavior in fields like social science and marketing . The authors categorize existing persona generation methods based on how much LLM-generated content is used, from simple structured data ( Meta Personas ) to highly detailed, freeform descr...

Large Language Models for Digital Twin Simulation 29.05.2025

Twin-2K-500: A dataset for building digital twins of over 2,000 people based on their answers to over 500 questions This academic paper introduces a novel and extensive dataset of over 2,000 human participants who answered more than 500 questions covering demographics, psychological traits, cognitive abilities, and economic behaviors across four waves of data collection. The dataset is designed to...

From RL Distillation to Autonomous LLM Agents 29.05.2025

We discuss the evolving role of Reinforcement Learning (RL) in Large Language Models (LLMs) . Initially, RL was primarily used as a distillation technique to align LLM outputs with preferences and improve performance on verifiable tasks by leveraging LLMs' ability to verify outputs better than generate them. However, the rise of LLM-based agents marks a shift where RL enables agents to learn a...

Prompting, Auto-Prompting, and Human-AI Communication 29.05.2025

We discuss the importance of prompts in human-Large Language Model (LLM) interaction, describing them as the primary interface through which users communicate intent and guide model behavior. However, they also critically examine the limitations of this prompt-centric approach , highlighting issues like LLM hallucinations, bias, reasoning struggles , and the "brittleness" of prompts that...

Textual Gradients for LLM Optimization 29.05.2025

We discuss the concept of textual gradient-based optimization for Large Language Model (LLM) workflows , contrasting it with traditional embedding space methods like soft prompt tuning. They introduce TextGrad as a foundational framework and focus heavily on LLM-AutoDiff as an advanced system designed to optimize complex, multi-component LLM applications represented as graphs, including features l...

Large Language Models as Markov Chains 28.05.2025

This academic paper explores the theoretical underpinnings of large language models (LLMs) , particularly their generalization abilities. The authors propose an equivalence between autoregressive transformer-based LLMs and finite-state Markov chains as a framework for analysis. They use this framework to examine LLM inference, generalization during pre-training on dependent data, and in-context le...

Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation 28.05.2025

This research explores Chain-of-Thought (CoT) reasoning in large language models by viewing it as a metastable Markov process . The authors model easy reasoning steps as dense clusters and hard steps as sparse connections, proving that search strategies rewarding these sparse edges improve efficiency by reducing the time to navigate between concept clusters. The study demonstrates that information...

Selective induction heads: how transformers select causal structures in context 28.05.2025

This research explores how transformers adapt to changing causal structures in data , which is crucial for understanding their success in language processing. They introduce a new test using interleaved Markov chains with varying "lags" or dependencies. The paper shows that a three-layer transformer can learn to identify the correct lag and predict the next token , a process termed selec...

The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains 28.05.2025

This document studies how transformers learn to predict sequential patterns in context , focusing on Markov Chains , a fundamental type of sequence. The research introduces a task called ICL-MC to investigate this, where models must learn from input sequences generated by different Markov Chains. The findings indicate that transformers develop "statistical induction heads" capable of cal...

How Transformers Learn Causal Structure with Gradient Descent 28.05.2025

This research investigates how transformers learn causal structure through gradient descent , focusing on their ability to perform in-context learning. The authors introduce a novel task involving random sequences with latent causal relationships and analyze a simplified two-layer transformer architecture. They demonstrate theoretically that gradient descent on the first attention layer recovers t...

Planning anything with rigor: general-purpose zero-shot planning with llm-based formalized programming 28.05.2025

This document introduces LLMFP, a framework for using Large Language Models (LLMs) to solve complex planning tasks by converting them into optimization problems solvable by formal planners like SMT solvers. It details the five-step process of LLMFP, which involves LLMs defining the problem, formulating variables, generating code, formatting results, and performing self-assessment and modification....

Automated Design of Agentic Systems 28.05.2025

This paper introduces Automated Design of Agentic Systems (ADAS) , a new research area aiming to automatically invent building blocks and design powerful agentic systems , arguing that this could be a faster and more effective approach than manual design, drawing parallels to the history of machine learning where learned solutions surpassed hand-designed ones. The paper proposes and evaluates Meta...

What’s the Magic Word? A Control Theory of LLM Prompting 28.05.2025

This paper investigates the mathematical basis of large language model (LLM) prompting by framing LLMs as discrete stochastic dynamical systems and employing control theory. The authors formalize LLM systems and introduce concepts of controllability and reachability in this context. They present a Self-Attention Control Theorem that provides a theoretical limit on controlling self-attention output...

BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling 27.05.2025

This academic paper from the University of Chicago addresses the problem of aligning large language models (LLMs) with human preferences. The authors analyze  best-of-n sampling , a technique where an LLM generates multiple responses and selects the best one, finding it to be  nearly optimal for maximizing win rate  while minimizing changes to other aspects of the output. To avoid the computationa...

RL with KL penalties is better viewed as Bayesian inference 27.05.2025

This paper proposes a novel Bayesian inference perspective for understanding and improving fine-tuning methods for large language models (LMs). The authors argue that traditional Reinforcement Learning (RL) approaches, when applied naively, lead to distribution collapse , where the LM generates only a limited set of high-reward outputs. They demonstrate that the commonly used KL-regularized RL obj...

Asymptotics of Language Model Alignment 27.05.2025

This academic paper investigates  language model alignment , a process of adjusting a base language model to better align with desired outcomes, often guided by a  reward model . It specifically examines two common alignment methods:  KL-constrained reinforcement learning (RL) , which maximizes reward while limiting divergence from the original model, and  best-of-N selection , where the highest-r...

Qwen 2.5, RL, and Random Rewards 27.05.2025

We investigate how various reward signals, even  spurious  and  random  ones, impact the performance of different language models fine-tuned for mathematical reasoning using Reinforcement Learning from Verbose Reasoning (RLVR). The research demonstrates that while  Qwen  models show significant improvement even with  weak  or  incorrect  rewards, this benefit is not universal, with  Llama  and  OL...

Theoretical guarantees on the best-of-n alignment policy 27.05.2025

This paper critically examines the  best-of-n policy , a common method for aligning generative language models by selecting the highest-reward sample from $n$ options drawn from a  reference policy . It  disproves a widely-used analytical formula  for the KL divergence between the best-of-n policy and the reference, proving that the formula is only an  upper bound . The authors analyze the conditi...

Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models 27.05.2025

This research paper explores using score matching —a technique for estimating the gradient of a data distribution's logarithm—to perform causal discovery in nonlinear additive noise models . The authors demonstrate that the causal graph's structure can be inferred from the score function , particularly its Jacobian . They propose a new algorithm, SCORE , which estimates the causal order by...

Improved Techniques for Training Score-Based Generative Models 27.05.2025

This research paper focuses on  improving score-based generative models (SBGMs)  to produce high-quality, high-resolution images. The authors identify limitations of existing SBGMs, specifically their inability to scale to higher resolutions and occasional training instability. They propose  new theoretical analyses  and techniques for  selecting noise scales , an  efficient method for incorporati...

Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator 27.05.2025

This paper introduces Disagreement-Aware Confidence Alignment (DACA) , an unsupervised method for calibrating the confidence of post-trained large language models (PoLMs) . While pre-trained language models (PLMs) are typically well-calibrated, post-training can lead to over-confidence , especially with limited labeled data. DACA addresses this by leveraging the well-calibrated confidence of PLMs...

AlphaEvolve: A coding agent for scientific and algorithmic discovery 27.05.2025

This paper introduces AlphaEvolve, a system designed to  automate the discovery of advanced algorithms  by leveraging large language models (LLMs) within an evolutionary framework. The system works by taking a user-defined problem and evaluation criteria, then iteratively generating and improving code solutions through an evolutionary process powered by LLM ensembles. AlphaEvolve has successfully...

Harnessing the Universal Geometry of Embeddings 27.05.2025

This academic paper presents vec2vec , a novel method for translating text embeddings between different models without requiring paired data or prior knowledge of the encoders. The authors demonstrate that this unsupervised technique successfully aligns embeddings from various models into a universal latent space , preserving the geometric structure and semantics of the original data. They show th...

Goal Inference using Reward-Producing Programs in a Novel Physics Environment 27.05.2025

This academic paper investigates how humans represent and infer goals , proposing that goals can be formalized as reward-producing programs . The researchers developed a physics-based game environment where participants created and demonstrated novel goals. By collecting natural language descriptions and formal scoring criteria , they analyzed the relationship between goal complexity, reward struc...

Listen to the Best AI papers explained podcast in Replaio

Radio and podcasts in one app - free, with no sign-up. Install today and do not miss the launch

Get it on Google Play

Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.