6 papers
Multilingual in Name Only? Cultural and Linguistic Weaknesses of LLMs in Urdu
Farah Adeeba, Abdul Rafae Khan, Rajesh Bhatt +1
Multilingual large language models (LLMs) are increasingly used for open-ended text generation, yet their behaviour in low-resource languages remains poorly understood. In this wor…
LLMs Underperform Graph-Based Parsers on Supervised Relation Extraction for Complex Graphs
Paolo Gajo, Domenic Rosati, Hassan Sajjad +1
Relation extraction represents a fundamental component in the process of creating knowledge graphs, among other applications. Large language models (LLMs) have been adopted as a pr…
LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering
Sing Hieng Wong, Hassan Sajjad, A. B. Siddique
Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult. Representation-level steering addresse…
Understanding Syntactic Generalization in Structure-inducing Language Models
David Arps, Hassan Sajjad, Laura Kallmeyer
Structure-inducing Language Models (SiLM) are trained on a self-supervised language modeling task, and induce a hierarchical sentence representation as a byproduct when processing…
UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu
Farah Adeeba, Brian Dillon, Hassan Sajjad +1
Multilingual Large Language Models (LLMs) have shown remarkable performance across various languages; however, they often include significantly less data for low-resource languages…
Multilingual Nonce Dependency Treebanks: Understanding how Language Models represent and process syntactic structure
David Arps, Laura Kallmeyer, Younes Samih +1
We introduce SPUD (Semantically Perturbed Universal Dependencies), a framework for creating nonce treebanks for the multilingual Universal Dependencies (UD) corpora. SPUD data sati…