ABD: Default Exception Abduction in Finite First Order Worlds
We introduce ABD, a benchmark for default-exception abduction over finite first-order worlds. Given a background theory with an abnormality predicate and a set of relational structures, a model must output a first-order formula that defines exceptions, restoring satisfiability while keeping exceptions sparse. We formalize three observation regimes (closed-world, existential completion, universal completion) with exact SMT verification. Evaluating ten frontier LLMs on 600 instances, the best models achieve high validity but parsimony gaps remain, and holdout evaluation reveals distinct generalization failure modes across regimes.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Signature-Based Abduction for Expressive Description Logics -- Technical Report
Signature-based abduction aims at building hypotheses over a specified set of names, the signature, that explain an observation relative to some background knowledge. This type of abduction is useful for tasks such as di…
Learning Abduction under Partial Observability
Juba recently proposed a formulation of learning abductive reasoning from examples, in which both the relative plausibility of various explanations, as well as which explanations are valid, are learned directly from data…
validTheory of Machine Learning with Limited Data
Application of machine learning may be understood as deriving new knowledge for practical use through explaining accumulated observations, training set. Peirce used the term abduction for this kind of inference. Here I f…
BIG-bench Machine LearningClusteringDecision MakingLearning Theory+1Modeling Variations of First-Order Horn Abduction in Answer Set Programming
We study abduction in First Order Horn logic theories where all atoms can be abduced and we are looking for preferred solutions with respect to three objective functions: cardinality minimality, coherence, and weighted a…
Natural Language UnderstandingExact Finite-Sample Variance Decomposition of Subagging: A Spectral Filtering Perspective
Standard resampling ratios (e.g., $α\approx 0.632$) are widely used as default baselines in ensemble learning for three decades. However, how these ratios interact with a base learner's intrinsic functional complexity in…
Ensemble Learning