Tag
This paper introduces a computational model that uses probabilistic reasoning over language and code to simulate human inductive learning and active inquiry, outperforming pure LLMs and classic Bayesian models in behavioral studies.
This paper proposes GRATE (Gated Rotary Attention for Temporal Encoding), a parameter-free temporal encoding method that enhances inductive knowledge graph foundation models by incorporating relative time differences and query-conditioned gating. It also introduces new inductive temporal knowledge graph benchmarks (GDELTIndT and WIKIIndT) to evaluate cross-dataset transfer, demonstrating improved performance over static base models.
InductWave proposes a wavelet-based inductive embedding method for multi-hop logical query answering on knowledge graphs, achieving competitive performance with fewer message-passing layers.
This paper introduces Program-based Posterior Training (PPT), a method that uses LLM-generated probabilistic programs to create distributional targets for fine-tuning inductive reasoning, improving estimation accuracy and calibration on held-out tasks and human-alignment benchmarks.
FalsifyBench is a new evaluation framework for assessing inductive reasoning in LLMs, inspired by the Wason 2-4-6 task, where agents discover hidden semantic rules by proposing examples and receiving feedback. Evaluation of 12 LLMs shows reasoning models outperform instruction-tuned models, with negative testing (hypothesis falsification) being the key driver of success.
Proposes KMAS, an adaptive negative sampling method to improve training of knowledge graph foundation models, achieving state-of-the-art results across 44 datasets.
MIND-Skill is a new framework introduced in this research paper that automates the generation of high-quality, reusable agent skills using multi-agent induction and deduction with quality guarantees via TextGrad optimization.