The paper delivers the first survey of abductive reasoning in LLMs, a unified two-stage taxonomy, a compact benchmark, and an analysis of gaps relative to deductive and inductive reasoning.
L2R² : Leveraging ranking for abductive reasoning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
ToolRec introduces dual-level calibration of click data and weighted KTO alignment to improve tool-invoking query recommendations in on-device assistants, reporting CTR gains in large-scale A/B tests.
citing papers explorer
-
Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs
The paper delivers the first survey of abductive reasoning in LLMs, a unified two-stage taxonomy, a compact benchmark, and an analysis of gaps relative to deductive and inductive reasoning.
-
ToolRec: Calibrated Preference Alignment for Query Recommendation in On-Device Assistants
ToolRec introduces dual-level calibration of click data and weighted KTO alignment to improve tool-invoking query recommendations in on-device assistants, reporting CTR gains in large-scale A/B tests.