MultiHashFormer enables hash-based autoregression in LMs by encoding tokens as multi-hash signatures, outperforming standard Transformers at 100M-3B scales while keeping parameter count constant for multilingual expansion.
Md Nesarul Hoque, Umme Salma, Md Jamal Uddin, Md Martuza Ahamad, and Sakifa Aktar
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CL 4years
2026 4verdicts
UNVERDICTED 4representative citing papers
IndiKLAR shows code-mixed inputs close the ~0.50 native-to-English LLM accuracy gap to within ~0.05, with a consistent performance flip point between native and code-mixed settings.
Multilingual models invert sentiment polarity 28.7% of the time on Bengali text and show asymmetric affective weighting plus a 57% rise in error on formal dialect compared with colloquial Bengali.
Modifying nationality and language parameters in English-centric personas for mental health dialogues introduces clinical inconsistencies across languages and causes LLM judges to perform inaccurately on non-English depression severity assessments.
citing papers explorer
-
MultiHashFormer: Hash-based Generative Language Models
MultiHashFormer enables hash-based autoregression in LMs by encoding tokens as multi-hash signatures, outperforming standard Transformers at 100M-3B scales while keeping parameter count constant for multilingual expansion.
-
Evaluating Cross-lingual Knowledge Consistency in Code-Mixed vis-a-vis Indian Languages using IndicKLAR
IndiKLAR shows code-mixed inputs close the ~0.50 native-to-English LLM accuracy gap to within ~0.05, with a consistent performance flip point between native and code-mixed settings.
-
Cross-Lingual Sentiment Misalignment: Auditing Multilingual Language Models for Inversion Risk, Dialectal Representation, and Affective Stability
Multilingual models invert sentiment polarity 28.7% of the time on Bengali text and show asymmetric affective weighting plus a 57% rise in error on formal dialect compared with colloquial Bengali.
-
Creating Multilingual Mental Health Dialogue Datasets: Limits of Persona-Based Localization via Nationality and Language
Modifying nationality and language parameters in English-centric personas for mental health dialogues introduces clinical inconsistencies across languages and causes LLM judges to perform inaccurately on non-English depression severity assessments.