4 papers
Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation
Yunting Song, Matthew Watson, Peter Grabowski +1
The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality. As datasets scale, massive preference and instruction-tuning corpora inevitably accumula…
Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
Shenao Zhang, Yaqing Wang, Yinxiao Liu +5
Large Language Models (LLMs) trained via Reinforcement Learning (RL) have exhibited strong reasoning capabilities and emergent reflective behaviors, such as rethinking and error co…
Revisiting Funnel Transformers for Modern LLM Architectures with Comprehensive Ablations in Training and Inference Configurations
DongHyun Choi, Lucas Spangher, Chris Hidey +2
Transformer-based Large Language Models, which suffer from high computational costs, advance so quickly that techniques proposed to streamline earlier iterations are not guaranteed…
Factored Agents: Decoupling In-Context Learning and Memorization for Robust Tool Use
Nicholas Roth, Christopher Hidey, Lucas Spangher +6
In this paper, we propose a novel factored agent architecture designed to overcome the limitations of traditional single-agent systems in agentic AI. Our approach decomposes the ag…