Large Language Model
ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution Haoran Y e
The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design. The long-standing endeavor of design automation has gained new momentum with the rise of large language models (LLMs).
QATCH: Benchmarking SQL-centric tasks with Table Representation Learning Models on Y our Data
We present QATCH (Query-Aided TRL Checklist), a toolbox to highlight TRL models' strengths and weaknesses on relational tables unseen at training time. For an input table, QATCH automatically generates a testing checklist tailored to QA and SP .
Can Language Models Solve Graph Problems in Natural Language?
Graph), a comprehensive benchmark of graph-based problem solving designed in natural language.
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion Filip Szatkowski IDEAS NCBR Warsaw University of Technology Bartosz Wรณjcik
Finally, we develop an efficient implementation that translates these computational savings into actual wall-clock speedup.
Learning Formal Mathematics From Intrinsic Motivation Gabriel Poesia 1 David Broman 4 Nick Haber 1,3 Noah D. Goodman
How did humanity coax mathematics from the รฆther?
RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
LLMs, but it remains unclear when it helps or hurts.
