activity
20242026
collaborators
Showing cs.CLShow all

9 papers · 1 filter

cs.CL2026

Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation

Tirth Bhatt, Naren Kumar S, Mayank Singh

Multilingual text embedding models are commonly adapted using a single training objective across diverse tasks, despite different tasks requiring fundamentally different optimizati…

cs.CL2026

Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models

Arya Shah, Himanshu Beniwal, Mayank Singh +1

Safety-aligned large language models often exhibit sycophancy, which is the tendency to affirm users' opinions regardless of factual accuracy. Although well-studied in English, its…

cs.CL2026

Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models

Himanshu Beniwal, Mayank Singh

Large language models frequently generate toxic, hateful, or harmful content, yet existing mitigation methods rely on costly retraining or output-level filtering with no mechanisti…

cs.CL2026

One Instruction Does Not Fit All: How Well Do Embeddings Align Personas and Instructions in Low-Resource Indian Languages?

Arya Shah, Himanshu beniwal, Mayank Singh

Aligning multilingual assistants with culturally grounded user preferences is essential for serving India's linguistically diverse population of over one billion speakers across mu…

cs.CL2025

Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs

Himanshu Beniwal, Sailesh Panda, Birudugadda Srivibhav +1

We explore \textbf{C}ross-lingual \textbf{B}ackdoor \textbf{AT}tacks (X-BAT) in multilingual Large Language Models (mLLMs), revealing how backdoors inserted in one language can aut…

cs.CL2025

COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing

Rajvee Sheth, Himanshu Beniwal, Mayank Singh

We introduce COMI-LINGUA, the largest manually annotated Hindi-English code-mixed dataset, comprising 125K+ high-quality instances across five core NLP tasks: Matrix Language Ident…