This work explored powerful explainers which use rules, where explanation instability stemming from training data becomes more apparent, and found that the rule-based method employed, BARBE, sharply increased in fidelity and stability when trained with the modified process, making BARBE+PBC which exceeded other methods that improve stability like S-LIME and LORE.
This work presents a comprehensive literature review of the current state of the subfield of XAI that consist of causality-motivated post-hoc XAI methods, and a causal framework for categorising XAI is introduced, and three types of post-hoc XAI methods are identified: observational methods, internally causal methods a...
Anna Rodum Bjøru, Helge Langseth, Inga Strümke et al.· Machine-mediated learning· 1 citation
BARBiE’s interactive, rule-based, and API-only design makes it a useful solution for explaining black-box models in enterprise settings, and it receives higher ratings for informativeness, understanding, trust, and satisfaction than all baselines.
The Rashomon Explanation paradigm is introduced, which builds a set of faithful, prediction-guiding explanations rather than a single one, and it is proved that this set is generally non-empty and that explanation fidelity bounds the performance of the models it guides.
This work shows that pooled refitting recomputes the inverse-Gram geometry used to weight source evidence, which can reverse shared preferences, and derive exact and approximate preservation conditions, and develops a three-stage audit that traces strict pairwise reversals through decision changes to task-defined utili...
The nature of test-time exploration in RLVR-trained LLMs is investigated by employing controlled maze-solving experiments and extracting a tree structure from mathematical reasoning traces (BODHI-Trees) based on semantic equivalence to delineate between entropy arising from stylistic variations and genuine inferential...
Soumadeep Saha, Krish Sharma, Akshay Chaturvedi et al.· 1 citation
Statistical tests are often asked to do too much. A single reported result is expected to describe what the observed data say, reassure readers about repeated-sampling behavior, and remain convincing when the working model is perturbed. Those tasks are connected, but they are not equivalent. Fisherian inductive inferen...
Subir Hait· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
