For tabular in-context learning models, recourse is well-defined, its cost is bounded and converges to classical linear recourse as context grows; ASR-ICL finds sparse recourse with fewer queries.
Distzo2: High-throughput and memory-efficient zeroth-order fine-tuning llms with distributed parallel computing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Algorithmic Recourse of In-Context Learning for Tabular Data
For tabular in-context learning models, recourse is well-defined, its cost is bounded and converges to classical linear recourse as context grows; ASR-ICL finds sparse recourse with fewer queries.