Skip to content
conftrace_
2026 EMNLP EMNLP 2026

CAML at SHROOM-Visions: Competency-Aware Intermediate-Layer Readouts for Multilingual Hallucination Localization

AbstractWe present CAML for multilingual hallucination localization at character level in SHROOM-Visions 2026. The system combines intermediate hidden states and four uncertainty features from a frozen Qwen3.5-4B evaluator, mapping supplied responses to character probabilities and five error categories. Probes from five cross-validation folds use temperature scaling and probability averaging, with about 3.37M trainable parameters in total. We compare readout depths under a common training and evaluation protocol. Selection on validation yields fixed layer 19, with macro character IoU of 0.3704; bootstrap intervals do not resolve its small differences from adjacent depth policies. Separately, the official challenge summary for the team gives macro IoU of 0.3825 and Spearman correlation of 0.4670, averaged over four languages. Independently trained Gemma probes also support localization, with fixed L24 scoring above both tested Gemma submissions combining layers. Across backbones, a single intermediate-layer readout consistently proves effective for localization, although the best depth remains backbone-specific rather than universal.

More from EMNLP 2026

All EMNLP 2026 papers →