Ordering retrieved documents along the reasoning chain and replacing the causal mask with a prefix mask during LoRA fine-tuning improves multi-hop QA accuracy; peak attention scores can select the best context order.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation
Ordering retrieved documents along the reasoning chain and replacing the causal mask with a prefix mask during LoRA fine-tuning improves multi-hop QA accuracy; peak attention scores can select the best context order.