QE should be reframed as a primary approach to source-grounded adequacy evaluation, rather than as a fallback motivated by missing references, and hybrid metrics whose designs explicitly prioritize source--hypothesis faithfulness are called for.
Baban Gain, Ramakrishna Appicharla, A. Ekbal· 0 citations
A post-hoc certification framework forparse autoencoders that provides a practical way to determine whether an SAE representation preserves enough of a frozen LM's predictive behavior to support certification of the original model.
This paper presents M-NLE, a compact knowledge-augmented multitask model for jointly detecting offensive memes and generating natural language explanations, and suggests that knowledge-augmented explanation generation is a practical direction for more interpretable offensive meme detection.
Dibyanayan Bandyopadhyay, Baban Gain, Samrat Mukherjee et al.· IEEE Access· 0 citations
COILD, an Indic-centric parallel corpus comprising over 1.16 million human-translated and human-verified sentence pairs, covers 20 Indian language pairs across the Indo-Aryan, Dravidian, Tibeto-Burman, and Austro-Asiatic language families, and provides a valuable training and evaluation resource for advancing multiling...
Kshetrimayum Boynao Singh, Nitin Kumar Mishra, P. Dutta et al.· arXiv.org· 0 citations
AUDITPLAN is a single-model plan-then-answer approach where the model first emits a compact structured safety plan and then answers conditioned on it, enabling machine-checkable auditing while remaining hidden from users at deployment.
Sai Sri Pushpa Jampani, Kshitij Mishra, A. Ekbal· 0 citations
ProNMT, a reward-guided iterative self-training method that combines sentence-level quality estimation with a signed confidence signal at generated pronoun positions, improves over context-aware supervised fine-tuning on BLEU and COMET and indicates that targeted linguistic feedback is most useful when combined with a...
Harshit Dhankhar, Baban Gain, A. Ekbal et al.· 0 citations
This work proposes CHAI, a general-purpose framework for enhancing LLM performance on CM tasks, focusing on CM translation, and incorporates LLM-generated domain knowledge as a constitution, enabling iterative response refinement.
Wen-Bo Zhang, Aditya Majumdar, A. Ekbal et al.· 7 citations· ⚡1
It is suggested that multilingual merging failures arise from target-side geometric misalignment within shared computational units, challenging the assumptions underlying standard weight-space merging for multilingual translation.
Baban Gain, A. Ekbal, T. Singh· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.