11 papers
Principled Thoughts for Latent Recursive LLM Systems
Fahd Seddik, Fatemeh Fard
Large language models can reason in continuous space instead of decoded text, by recurring on their own hidden states or by passing those states between agents, while training supe…
TokenScope: Token-Level Explainability and Interpretability for Code-Oriented Tasks in Large Language Models
Amirreza Esmaeili, Fatemeh Fard
Understanding how Large Language Models (LLMs) make token-level decisions during code generation remains a major challenge for both researchers and practitioners. While recent tool…
What Makes a Latent Thought Valid? Defining and Auditing Thought Representations in LLMs
Fahd Seddik, Fatemeh Fard
Chain-of-Thought (CoT) reasoning improves the performance of Large Language Models (LLMs), yet it writes steps as text and follows one reasoning path at a time, which limits the ca…
Standing on the Shoulders of Giants: Stabilized Knowledge Distillation for Cross--Language Code Clone Detection
Mohamad Khajezade, Fatemeh H. Fard, Mohamed Sami Shehata
Cross-language code clone detection (X-CCD) is challenging because semantically equivalent programs written in different languages often share little surface similarity. Although l…
Context-Augmented Code Generation Using Programming Knowledge Graphs
Shahd Seddik, Fahd Seddik, Iman Saberi +3
Large Language Models (LLMs) excel at code generation but struggle with complex problems. Retrieval-Augmented Generation (RAG) mitigates this issue by integrating external knowledg…
FISCAL: Financial Synthetic Claim-document Augmented Learning for Efficient Fact-Checking
Rishab Sharma, Iman Saberi, Elham Alipour +2
Financial applications of large language models (LLMs) require factual reliability and computational efficiency, yet current systems often hallucinate details and depend on prohibi…
Analysis of AdvFusion: Adapter-based Multilingual Learning for Code Large Language Models
Amirreza Esmaeili, Fahd Seddik, Yongyi Ji +2
Programming languages can benefit from one another by utilizing a language model for software engineering tasks. Full fine-tuning and Parameter Efficient Fine-Tuning (PEFT) of Code…
Context-Augmented Code Generation Using Programming Knowledge Graphs
Iman Saberi, Fatemeh Fard
Large Language Models (LLMs) and Code-LLMs (CLLMs) have significantly improved code generation, but, they frequently face difficulties when dealing with challenging and complex pro…
Do Current Language Models Support Code Intelligence for R Programming Language?
ZiXiao Zhao, Fatemeh H. Fard
Recent advancements in developing Pre-trained Language Models for Code (Code-PLMs) have urged many areas of Software Engineering (SE) and brought breakthrough results for many SE t…
Empirical Studies of Parameter Efficient Methods for Large Language Models of Code and Knowledge Transfer to R
Amirreza Esmaeili, Iman Saberi, Fatemeh H. Fard
Parameter Efficient Fine-Tuning (PEFT) methods are proposed as an alternative fine-tuning approach for Large Language Models (LLM) to minimize high training costs. While prior rese…
Studying Vulnerable Code Entities in R
Zixiao Zhao, Millon Madhur Das, Fatemeh H. Fard
Pre-trained Code Language Models (Code-PLMs) have shown many advancements and achieved state-of-the-art results for many software engineering tasks in the past few years. These mod…