works on

From the 1 of 12 linked papers with an AI index.

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

Pluralis v0.1: Towards a Multicultural, Multimodal, Multilingual Benchmark for AI Risk and Reliability

Alicia Parrish, Rajat Shinde, Sanket Badhe +57

Current AI safety evaluation and benchmarking frameworks predominantly rely on Western-centric culture-agnostic defaults that mask critical regional laws, socio-linguistic nuances,…

cs.CL2026

Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning

Sanket Badhe, Deep Shah

Advanced reasoning typically requires Chain-of-Thought prompting, which is accurate but incurs prohibitive latency and substantial test-time inference costs. The standard alternati…

cs.CL2026

The Silent Vote: Improving Zero-Shot LLM Reliability by Aggregating Semantic Neighborhoods

Sanket Badhe, Priyanka Tiwari, Deep Shah

Large Language Models are increasingly used as zero-shot classifiers in complex reasoning tasks. However, standard constrained decoding suffers from a phenomenon we define as Renor…

cs.CL2026

CROP: Token-Efficient Reasoning in Large Language Models via Regularized Prompt Optimization

Deep Shah, Sanket Badhe, Nehal Kathrotia +1

Large Language Models utilizing reasoning techniques improve task performance but incur significant latency and token costs due to verbose generation. Existing automatic prompt opt…

cs.CL2026

Large Language Models in the Abuse Detection Pipeline

Suraj Kath, Sanket Badhe, Preet Shah +2

Online abuse has grown increasingly complex, spanning toxic language, harassment, manipulation, and fraudulent behavior. Traditional machine-learning approaches dependent on static…

cs.CL20261 cited

Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications

Sanket Badhe, Deep Shah, Nehal Kathrotia

Large language models (LLMs) are trained on web-scale corpora that exhibit steep power-law distributions, in which the distribution of knowledge is highly long-tailed, with most ap…