activity
20242026
most citedChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems

4 citations · 18 across the 27 of their papers we have counts for

collaborators
Showing cs.CLShow all

20 papers · 1 filter

cs.CL2026

MUDDLE: Measuring Understanding of Documents under Distractor and Length Effects

Jason Luo, Saibilila Abudukelimu, Judy Song +4

Document question-answering systems increasingly answer questions over collections of retrieved documents rather than one clean source, so robustness to distracting context matters…

cs.CL2025

Direct Confidence Alignment: Aligning Verbalized Confidence with Internal Confidence In Large Language Models

Glenn Zhang, Treasure Mayowa, Jason Fan +4

Producing trustworthy and reliable Large Language Models (LLMs) has become increasingly important as their usage becomes more widespread. Calibration seeks to achieve this by impro…

cs.CL2025★ 3 cited

Adaptive Linguistic Prompting (ALP) Enhances Phishing Webpage Detection in Multimodal Large Language Models

Atharva Bhargude, Ishan Gonehal, Dave Yoon +4

Phishing attacks represent a significant cybersecurity threat, necessitating adaptive detection techniques. This study explores few-shot Adaptive Linguistic Prompting (ALP) in dete…

cs.CL2025

Error Reflection Prompting: Can Large Language Models Successfully Understand Errors?

Jason Li, Lauren Yraola, Kevin Zhu +1

Prompting methods for language models, such as Chain-of-thought (CoT), present intuitive step-by-step processes for problem solving. These methodologies aim to equip models with a…

cs.CL2025

Pruning for Performance: Efficient Idiom and Metaphor Classification in Low-Resource Konkani Using mBERT

Timothy Do, Pranav Saran, Harshita Poojary +4

In this paper, we address the persistent challenges that figurative language expressions pose for natural language processing (NLP) systems, particularly in low-resource languages…

cs.CL2025

MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered

Imran Mirza, Cole Huang, Ishwara Vasista +4

Multi-agent systems, which consist of multiple AI models interacting within a shared environment, are increasingly used for persona-based interactions. However, if not carefully de…