6 papers
HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning
Donggyun Kim, Jack Lu, Chanwoo Kim +2
Long-form thinking traces can substantially improve the multi-step reasoning performance of large language models (LLMs), but they introduce high inference-time overhead, with late…
Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting
Hui Dai, Ryan Teehan, Parsa Torabian +1
Probabilistic forecasting estimates the likelihood of uncertain future events. To improve LLM forecasting, existing methods typically learn from binary outcomes to output verbalize…
Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents
Kangsan Kim, Minki Kang, Taeil Kim +3
Memory-based self-evolution has emerged as a promising paradigm for coding agents. However, existing approaches typically restrict memory utilization to homogeneous task domains, f…
SkillFactory: Self-Distillation For Learning Cognitive Behaviors
Zayne Sprague, Jack Lu, Manya Wadhwa +3
Reasoning models leveraging long chains of thought employ various cognitive skills, such as verification of their answers, backtracking, retrying by an alternate method, and more.…
When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers
Jack Lu, Ryan Teehan, Jinran Jin +1
Large language models (LLMs) can act as both problem solvers and solution verifiers, where the latter select high-quality answers from a pool of solver-generated candidates. This r…
Context Tuning for In-Context Optimization
Jack Lu, Ryan Teehan, Zhenbang Yang +1
We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of large language models (LLMs) without weight updates. In-Context Learning…