Study tests cross-lingual concept transfer in Bangla idiom subspaces
English class-mean readouts beat zero-shot nulls in 8 of 12 tests, but English-fitted erasure barely changes Bangla accuracy.
Stories per day · 30 days
1 RSS
Relatedbangla1bilingual-models1concept-subspaces1eye-tracking1interpretability1leace1low-resource1second-language1speech-synthesis1surprisal1text-to-speech1vocabulary-expansion1
9 stories, newest first · one card per story
Stories tagged #cross-lingual
Bilingual models better predict L2 reading when L1 matches
The advantage appears in late eye-tracking measures, depends on script overlap, and peaks for intermediate-proficiency readers.
SEAM expands TTS vocabularies without paired audio fine-tuning
The method matches or approaches baselines with up to four times less data across three languages and two architectures.
Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII
Training-data extraction of memorized PII transfers from English prompts into four other languages.
Multilingual GSM-Symbolic: What determines capability transfer across languages?
Multilingual GSM-Symbolic finds model size, resources, reasoning, and typology drive cross-lingual math transfer.
Cross-Lingual Alignment for Decoder-Only Models using MoE Routers
Aligning MoE router outputs improved cross-lingual transfer in four open-source decoder-only models.
Linguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware Unlearning
A 174-language benchmark shows LLM unlearning fails across languages, and COVER improves cross-lingual erasure.
Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning
Accent Analogy Guidance raises cross-lingual TTS speaker similarity at equal accent across several open models.
Right Tool, Right Job: Native-Language Evaluation, Tokenizer Sensitivity, and Methodological Findings from a French-Only BabyLM
French BabyLM entry METRON-FR (125M GPT-2, 92.47M words) shows tokenizer artifacts dominate child-scale zero-shot evaluation; proposes standard diagnostics.