DuDi is a dual-signal distillation method with cross-lingual verbalizer that improves multilingual SLM performance on SEA languages and outperforms baselines on SEA-HELM.
Proceedings of the 57th
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
SOTA claims based on aggregate benchmark scores frequently lack evidence for true model superiority beyond marginal mean improvements.
LLMs show minimal sociodemographic disparities in advice because they infer user demographics poorly from history; conversation topics are the main predictor and act as proxies for groups.
citing papers explorer
-
DuDi: Dual-Signal Distillation with Cross-Lingual Verbalizer
DuDi is a dual-signal distillation method with cross-lingual verbalizer that improves multilingual SLM performance on SEA languages and outperforms baselines on SEA-HELM.
-
Position: State-of-the-Art Claims Require State-of-the-Art Evidence
SOTA claims based on aggregate benchmark scores frequently lack evidence for true model superiority beyond marginal mean improvements.
-
Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers
LLMs show minimal sociodemographic disparities in advice because they infer user demographics poorly from history; conversation topics are the main predictor and act as proxies for groups.