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
Ellipsoidal Methods for Adaptive Choice-Based Conjoint Analysis 11.04.2025 14:35
The paper "Ellipsoidal Methods for Adaptive Choice-Based Conjoint Analysis" introduces a novel approach to designing adaptive questionnaires for understanding consumer preferences. It addresses limitations in existing geometric methods, like the polyhedral method, particularly with high response error rates. The paper proposes an ellipsoidal method that uses normal approximations withi...
Adaptive Polyhedral Methods for Conjoint Analysis 11.04.2025 20:04
This 2002 paper introduces a novel method for adaptive conjoint analysis, termed Fast Polyhedral Adaptive Conjoint Estimation. Drawing upon mathematical programming, it aims to efficiently and accurately estimate customer preferences with fewer questions, adapting each subsequent query based on individual responses. The technique uses polyhedral geometry and interior-point algorithms to select...
MSL: Enhancing LLM Recommenders via Masked Softmax Loss 11.04.2025 15:56
The paper "MSL: Not All Tokens Are What You Need for Tuning LLM as a Recommender" identifies limitations of using the standard language modeling loss for fine-tuning large language models as recommendation systems. Specifically, it points out the divergence from recommendation goals and the misleading negative signals arising from treating all non-positive item descriptions as nega...
Self-Supervised Deep Reinforcement Learning for Optimal Question Ranking 11.04.2025 21:05
Tkachenko, Jedidi, and Ansari's paper addresses the challenge of lengthy consumer questionnaires, which can increase costs and decrease response quality. They propose a novel solution using self-supervised deep reinforcement learning to rank questions by their information value. Their method outperforms traditional question ranking and competes with unordered subset selection techniques. ...
Adaptive Language Elicitation for Latent Information Discovery 10.04.2025 16:55
2504.04204 : Adaptive Elicitation of Latent Information Using Natural Language This research paper introduces a novel framework for adaptive information elicitation using natural language, addressing the challenge of understanding latent entities that cannot be directly observed. This framework employs meta-learned language models to predict future observations and quantify uncertainty, enab...
LLM Persona Bias: Promise and Peril in Simulation 10.04.2025 17:37
They discuss using large language models (LLMs) to generate synthetic human personas for simulations across various fields. The authors highlight that while LLM-generated personas offer a scalable and cost-effective alternative to traditional data collection, current methods lack rigor and introduce significant biases. Through experiments like predicting election outcomes and general opinion su...
AutoTools: Automating Tool Use for Large Language Models 10.04.2025 19:52
This paper introduces AutoTools , a novel framework designed to empower large language models (LLMs) to function as automated tool agents. This system enables LLMs to automatically transform tool documentation into callable functions and subsequently integrate these functions into executable programs to solve practical tasks. The authors identify limitations in previous manual approaches for...
Tool Learning with Large Language Models: A Comprehensive Survey 10.04.2025 23:29
This survey examines the burgeoning field of tool learning with large language models (LLMs) , a paradigm where LLMs enhance their capabilities by using external tools to solve complex problems. The authors systematically explore why tool learning is beneficial , detailing advantages like improved knowledge acquisition and robustness, and how it is implemented , outlining a four-stage workflow...
All Roads Lead to Likelihood: RL for Fine-Tuning Value 08.04.2025 24:16
This research paper investigates why reinforcement learning (RL) often improves the fine-tuning of large language models compared to direct maximum likelihood estimation (MLE). The authors explore the theoretical equivalence of these methods under certain conditions, demonstrating that they should ideally yield similar results. However, empirical evidence shows RL-based fine-tuning, particularly...
ATLAS: Tuning Agents via Critical Step Learning 08.04.2025 20:00
This paper introduces ATLAS, a novel method for enhancing large language model agents by selectively fine-tuning them on critical steps identified within expert action sequences. This approach, which uses another LLM to pinpoint crucial moments like planning, key observations, significant actions, and self-correction , aims to overcome limitations of traditional full-trajectory imitation learn...
Thinking Faster by Writing Less: Chain of Draft Reasoning 08.04.2025 18:36
This research paper introduces Chain of Draft (CoD) , a novel prompting strategy for Large Language Models (LLMs) designed to mimic efficient human reasoning by generating concise intermediate thoughts. Unlike the verbose Chain-of-Thought (CoT) prompting, CoD encourages LLMs to produce minimal yet informative outputs at each step, leading to comparable or superior accuracy with significantly re...
Meta Plan Optimization for Boosting LLM Agents 08.04.2025 19:01
This research paper introduces Meta Plan Optimization (MPO), a new framework to improve how large language model agents plan for tasks. MPO uses high-level, general instructions called meta plans to guide the agents, helping them avoid planning errors and the need for retraining on each new task. The framework includes a meta planner that generates these guiding plans and is refined based on feed...
L1: Length Controlled Reasoning with Reinforcement Learning 08.04.2025 16:59
This research paper introduces Length Controlled Policy Optimization (LCPO) , a reinforcement learning technique that enables reasoning language models to control the length of their generated thought processes based on user-specified constraints. By training a model called L1 with LCPO, the authors demonstrate precise management of reasoning length, allowing for a trade-off between computatio...
WikiBigEdit: Benchmarking Lifelong Knowledge Editing in LLMs 08.04.2025 20:12
This introduces WikiBigEdit , a new large-scale benchmark for evaluating how well large language models can continuously update their factual knowledge over time, using real-world edits from Wikidata. The authors find that existing knowledge editing techniques struggle with the scale and sequential nature of these real-world updates . In contrast, simpler methods like retrieval augmentation an...
PLAN-AND-ACT: LLM Agent Planning with Synthetic Data 08.04.2025 14:32
This research paper introduces PLAN-AND-ACT , a new framework designed to enhance the ability of language agents to handle complex, long-horizon tasks. This system separates the process into two modules: a PLANNER , which generates high-level, structured plans, and an EXECUTOR , which translates these plans into specific actions within an environment. To effectively train the PLANNER , the aut...
SEARCH-R1: LLMs Learn to Reason and Search via Reinforcement Learning 08.04.2025 23:54
This research paper introduces SEARCH-R1 , a novel framework that enhances large language models by enabling them to learn to effectively use search engines through reinforcement learning. This approach allows LLMs to autonomously generate search queries and leverage retrieved information during their reasoning process, improving performance on question-answering tasks . Unlike traditional met...
The Theory of the Firm: Information, Incentives, and Organization 08.04.2025 24:39
This Handbook of Industrial Organization provides a comprehensive overview of the theory of the firm , moving beyond traditional market analysis to explore internal firm behavior and organization . It examines the boundaries of firms , issues of capital structure , the impact of separated ownership and control , and the complexities of internal hierarchies . The authors synthesize various t...
Four Formalizable Theories of the Firm 08.04.2025 32:04
This paper by Robert Gibbons explores four fundamental theories of the firm , aiming to clarify their core tenets, distinctions, and potential for integration. It examines the rent-seeking, property-rights, incentive-system, and adaptation theories , tracing their intellectual origins and highlighting key contributions from prominent scholars. The essay formally models three of these theories ...
Efficient Tool Use with Chain-of-Abstraction Reasoning 06.04.2025 21:21
arXiv:2401.17464 Efficient Tool Use with Chain-of-Abstraction Reasoning Silin Gao , Jane Dwivedi-Yu , Ping Yu , Xiaoqing Ellen Tan , Ramakanth Pasunuru , Olga Golovneva , Koustuv Sinha , Asli Celikyilmaz , Antoine Bosselut , Tianlu Wang This research paper introduces Chain-of-Abstraction (CoA) , a novel method designed to enhance the ability of large language models (LLMs) to effectively...
CodeTool: Process Supervision for Enhanced LLM Tool Invocation 06.04.2025 17:01
We discuss CodeTool, a novel framework that enhances how large language models utilize external tools by generating and supervising code execution step-by-step. This approach uses process rewards: an "On-the-spot Reward" for immediate code correctness and a "Latent Reward" to guide towards effective problem-solving paths, with the latter estimated by a trained model. CodeTool leverages the verifia...
Evaluating LLM Agents in Multi-Turn Conversations: A Survey 06.04.2025 29:26
This survey systematically investigates how to evaluate large language model-based agents designed for multi-turn conversations. The authors reviewed nearly 250 academic papers to understand current evaluation practices, establishing a structured framework with two key taxonomies. One taxonomy defines what to evaluate, encompassing aspects like task completion, response quality, user experience, m...
Epistemic Alignment in User-LLM Knowledge Delivery 06.04.2025 17:00
This paper explores the epistemic alignment problem in user interactions with Large Language Models (LLMs), highlighting the mismatch between user knowledge preferences and the limited ways to express them. The authors propose the Epistemic Alignment Framework , consisting of ten challenges derived from epistemology, to bridge this gap and create a shared vocabulary. Through an analysis of user...
MCP is (not) all you need 06.04.2025 28:54
We discuss Model Context Protocol (MCP) , positioning it as a standardized, open-source protocol championed by Anthropic to unify how large language models (LLMs) interact with external APIs, akin to a USB-C for AI. It explains that while previous methods for LLM integration existed, MCP offers a consistent interface using JSON-RPC , demonstrated through examples like tools/list and tools/call, f...
AI, Human Skills, and Competitive Advantage in Chess 05.04.2025 23:24
We investigate how artificial intelligence (AI) impacts competitive advantage , employing a resource-based view . Through a study of chess tournaments with human, AI, and hybrid players, the authors find that AI adoption leads to both the obsolescence of traditional human skills and the emergence of new advantages stemming from human-machine collaboration. This substitution and complementatio...
Inference-Time Scaling for Generalist Reward Modeling 04.04.2025 21:48
This paper explores how to improve the effectiveness of reward modeling (RM) for large language models (LLMs) by utilizing more computational resources during inference. The authors focus on generalist RM, aiming for accurate reward signals across diverse queries, not just verifiable ones. To achieve this, they introduce Self-Principled Critique Tuning (SPCT), a novel learning method that enables...
Similar podcasts
Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.