Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering
Purva Chiniya, Kevin Scaria, Sagar Chaturvedi
Large language models (LLMs) remain susceptible to jailbreak and direct prompt-injection attacks, yet the strongest defensive filters frequently over-refuse benign queries and degr…
cs.CL2024
Cutting Through the Noise: Boosting LLM Performance on Math Word Problems
Ujjwala Anantheswaran, Himanshu Gupta, Kevin Scaria +3
Large Language Models (LLMs) excel at various tasks, including solving math word problems (MWPs), but struggle with real-world problems containing irrelevant information. To addres…
cs.CL2024
Embarrassingly Simple Unsupervised Aspect Based Sentiment Tuple Extraction
Kevin Scaria, Abyn Scaria, Ben Scaria
Aspect Based Sentiment Analysis (ABSA) tasks involve the extraction of fine-grained sentiment tuples from sentences, aiming to discern the author's opinions. Conventional methodolo…