11 papers
Constrained Semantic Decompression in LLMs through Persian Proverb-Conditioned Story Generation
Zahra Habibzadeh, Paria Khoshtab, Amir Mesbah +1
Transforming a dense, abstract proverb into an engaging and morally faithful narrative requires deep cultural understanding and robust semantic grounding. We frame this problem as…
GhazalBench: Evaluating LLM Understanding and Canonical Surface-Form Access in Persian Ghazals
Ghazal Kalhor, Yadollah Yaghoobzadeh
Persian poetry plays an active role in Iranian cultural practice, where verses by canonical poets such as Hafez are frequently quoted, paraphrased, or completed from partial cues.…
Layer-wise Positional Bias in Short-Context Language Modeling
Maryam Rahimi, Mahdi Nouri, Yadollah Yaghoobzadeh
Transformer language models systematically prefer tokens at specific input positions regardless of semantic relevance---a phenomenon known as positional bias. Prior work characteri…
A Dual-Axis Taxonomy of Knowledge Editing for LLMs: From Mechanisms to Functions
Amir Mohammad Salehoof, Ali Ramezani, Yadollah Yaghoobzadeh +1
Large language models (LLMs) acquire vast knowledge from large text corpora, but this information can become outdated or inaccurate. Since retraining is computationally expensive,…
GenKnowSub: Improving Modularity and Reusability of LLMs through General Knowledge Subtraction
Mohammadtaha Bagherifard, Sahar Rajabi, Ali Edalat +1
Large language models often struggle with zero-shot generalization, and several modular approaches have been proposed to address this challenge. Yet, we hypothesize that a key limi…
Explanations of Large Language Models Explain Language Representations in the Brain
Maryam Rahimi, Yadollah Yaghoobzadeh, Mohammad Reza Daliri
Large Language Model (LLM) representations are known to align with brain activity during language processing, but it remains unclear what drives this alignment. We test whether exp…