26 citations · 74 across the 49 of their papers we have counts for
54 papers
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…
Neuron-Level Analysis of Cultural Understanding in Large Language Models
Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala +1
As large language models (LLMs) are increasingly deployed worldwide, ensuring their fair and comprehensive cultural understanding is important. However, LLMs exhibit cultural bias…
Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset
Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala +1
Large language models (LLMs) exhibit social biases, prompting the development of various debiasing methods. However, debiasing methods may degrade the capabilities of LLMs. Previou…
Annotating Training Data for Conditional Semantic Textual Similarity Measurement using Large Language Models
Gaifan Zhang, Yi Zhou, Danushka Bollegala
Semantic similarity between two sentences depends on the aspects considered between those sentences. To study this phenomenon, Deshpande et al. (2023) proposed the Conditional Sema…
SCDTour: Embedding Axis Ordering and Merging for Interpretable Semantic Change Detection
Taichi Aida, Danushka Bollegala
In Semantic Change Detection (SCD), it is a common problem to obtain embeddings that are both interpretable and high-performing. However, improving interpretability often leads to…
Evaluating the Evaluation of Diversity in Commonsense Generation
Tianhui Zhang, Bei Peng, Danushka Bollegala
In commonsense generation, given a set of input concepts, a model must generate a response that is not only commonsense bearing, but also capturing multiple diverse viewpoints. Num…
CASE -- Condition-Aware Sentence Embeddings for Conditional Semantic Textual Similarity Measurement
Gaifan Zhang, Yi Zhou, Danushka Bollegala
The meaning conveyed by a sentence often depends on the context in which it appears. Despite the progress of sentence embedding methods, it remains unclear as how to best modify a…
Evaluating the Effect of Retrieval Augmentation on Social Biases
Tianhui Zhang, Yi Zhou, Danushka Bollegala
Retrieval Augmented Generation (RAG) has gained popularity as a method for conveniently incorporating novel facts that were not seen during the pre-training stage in Large Language…
Improving Unsupervised Constituency Parsing via Maximizing Semantic Information
Junjie Chen, Xiangheng He, Yusuke Miyao +1
Unsupervised constituency parsers organize phrases within a sentence into a tree-shaped syntactic constituent structure that reflects the organization of sentence semantics. Howeve…
Investigating the Contextualised Word Embedding Dimensions Specified for Contextual and Temporal Semantic Changes
Taichi Aida, Danushka Bollegala
The sense-aware contextualised word embeddings (SCWEs) encode semantic changes of words within the contextualised word embedding (CWE) spaces. Despite the superior performance of S…
Evaluating Short-Term Temporal Fluctuations of Social Biases in Social Media Data and Masked Language Models
Yi Zhou, Danushka Bollegala, Jose Camacho-Collados
Social biases such as gender or racial biases have been reported in language models (LMs), including Masked Language Models (MLMs). Given that MLMs are continuously trained with in…
Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learning
Tianhui Zhang, Bei Peng, Danushka Bollegala
Generative Commonsense Reasoning (GCR) requires a model to reason about a situation using commonsense knowledge, while generating coherent sentences. Although the quality of the ge…
Unsupervised Parsing by Searching for Frequent Word Sequences among Sentences with Equivalent Predicate-Argument Structures
Junjie Chen, Xiangheng He, Danushka Bollegala +1
Unsupervised constituency parsing focuses on identifying word sequences that form a syntactic unit (i.e., constituents) in target sentences. Linguists identify the constituent by e…
Improving Pre-trained Language Model Sensitivity via Mask Specific losses: A case study on Biomedical NER
Micheal Abaho, Danushka Bollegala, Gary Leeming +2
Adapting language models (LMs) to novel domains is often achieved through fine-tuning a pre-trained LM (PLM) on domain-specific data. Fine-tuning introduces new knowledge into an L…
Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings
Gaifan Zhang, Yi Zhou, Danushka Bollegala
Sentence embeddings produced by Pretrained Language Models (PLMs) have received wide attention from the NLP community due to their superior performance when representing texts in n…
A Semantic Distance Metric Learning approach for Lexical Semantic Change Detection
Taichi Aida, Danushka Bollegala
Detecting temporal semantic changes of words is an important task for various NLP applications that must make time-sensitive predictions. Lexical Semantic Change Detection (SCD) ta…
Eagle: Ethical Dataset Given from Real Interactions
Masahiro Kaneko, Danushka Bollegala, Timothy Baldwin
Recent studies have demonstrated that large language models (LLMs) have ethical-related problems such as social biases, lack of moral reasoning, and generation of offensive content…
Evaluating Gender Bias in Large Language Models via Chain-of-Thought Prompting
Masahiro Kaneko, Danushka Bollegala, Naoaki Okazaki +1
There exist both scalable tasks, like reading comprehension and fact-checking, where model performance improves with model size, and unscalable tasks, like arithmetic reasoning and…