26 citations · 74 across the 49 of their papers we have counts for
7 papers · 1 filter
Beyond Model Weights: Sampling-Dependent Fairness in Diffusion Language Models
Koshiro Saito, Daisuke Oba, Diasuke Oba +2
Diffusion language models (DLMs) are emerging as a practical alternative to autoregressive language models (ARLMs), yet their fairness remains largely uncharacterized. DLMs introdu…
Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models
Lingfang Li, Procheta Sen, Shubham Das +1
Fine-tuning has emerged as a widely adopted approach for adapting LLMs to a variety of downstream tasks. However, how it reshapes their internal mechanisms remains poorly understoo…
WiC is Not WSD: A Study on LLMs and Lexical Ambiguity Resolution
Yi Zhou, Kiamehr Rezaee, Danushka Bollegala +2
Word-in-Context (WiC) remains challenging for language models, despite recent progress on lexical-semantic tasks. We hypothesise that this difficulty arises not only from comparing…
Cross-Lingual Representation Alignment by Token-Level Optimal Transport in a Language-Agnostic Space
Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala +1
Cross-lingual alignment (CLA) aims to align the representations of large language models (LLMs) across languages, enabling cross-lingual transfer to improve multilingual capabiliti…
Synthetic Data Generation for Training Diversified Commonsense Reasoning Models
Tianhui Zhang, Bei Peng, Danushka Bollegala
Conversational agents are required to respond to their users not only with high quality (i.e. commonsense bearing) responses, but also considering multiple plausible alternative sc…
Map of Encoders -- Mapping Sentence Encoders using Quantum Relative Entropy
Gaifan Zhang, Danushka Bollegala
We propose a method to compare and visualise sentence encoders at scale by creating a map of encoders where each sentence encoder is represented in relation to the other sentence e…
Stopping Computation for Converged Tokens in Masked Diffusion-LM Decoding
Daisuke Oba, Danushka Bollegala, Masahiro Kaneko +1
Masked Diffusion Language Models generate sequences via iterative sampling that progressively unmasks tokens. However, they still recompute the attention and feed-forward blocks fo…