Related papers: FrameEOL: Semantic Frame Induction using Causal La…
The recent advancements in generative language models have demonstrated their ability to memorize knowledge from documents and recall knowledge to respond to user queries effectively. Building upon this capability, we propose to enable…
Vision-language models such as CLIP have shown impressive capabilities in encoding texts and images into aligned embeddings, enabling the retrieval of multimodal data in a shared embedding space. However, these embedding-based models still…
Contextualised word embeddings generated from Neural Language Models (NLMs), such as BERT, represent a word with a vector that considers the semantics of the target word as well its context. On the other hand, static word embeddings such as…
Large Language Models (LLMs) are seeing significant adoption in every type of organization due to their exceptional generative capabilities. However, LLMs are found to be vulnerable to various adversarial attacks, particularly prompt…
Although existing model editing methods perform well in recalling exact edit facts, they often struggle in complex scenarios that require deeper semantic understanding rather than mere knowledge regurgitation. Leveraging the strong…
Augmenting large language models (LLMs) with external tools has emerged as a promising approach to solving complex problems. However, traditional methods, which finetune LLMs with tool demonstration data, can be both costly and restricted…
This paper discusses the methods that we used for our submissions to the WMT 2023 Terminology Shared Task for German-to-English (DE-EN), English-to-Czech (EN-CS), and Chinese-to-English (ZH-EN) language pairs. The task aims to advance…
Multimodal Recommender Systems aim to improve recommendation accuracy by integrating heterogeneous content, such as images and textual metadata. While effective, it remains unclear whether their gains stem from true multimodal understanding…
Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily…
We explore the ability of large language models (LLMs) to act as speech recognition post-processors that perform rescoring and error correction. Our first focus is on instruction prompting to let LLMs perform these task without fine-tuning,…
Pre-trained vision-language models (VLMs) have shown remarkable generalization capabilities via prompting, which leverages VLMs as knowledge bases to extract information beneficial for downstream tasks. However, existing methods primarily…
The growing number of generative AI-based dialogue systems has made their evaluation a crucial challenge. This paper presents our contribution to this important problem through the Dialogue System Technology Challenge (DSTC-12, Track 1),…
Topic segmentation using generative Large Language Models (LLMs) remains relatively unexplored. Previous methods use semantic similarity between sentences, but such models lack the long range dependencies and vast knowledge found in LLMs.…
In this paper, we study an under-explored area of language and vocabulary learning: keyword mnemonics, a technique for memorizing vocabulary through memorable associations with a target word via a verbal cue. Typically, creating verbal cues…
Large vision-language models (VLMs) have shown significant performance boost in various application domains. However, adopting them to deal with several sequentially encountered tasks has been challenging because finetuning a VLM on a task…
Quantum Language Models (QLMs) in which words are modelled as quantum superposition of sememes have demonstrated a high level of model transparency and good post-hoc interpretability. Nevertheless, in the current literature word sequences…
Large language models (LLMs) have been effectively used for many computer vision tasks, including image classification. In this paper, we present a simple yet effective approach for zero-shot image classification using multimodal LLMs.…
With an increasing number of parameters and pre-training data, generative large language models (LLMs) have shown remarkable capabilities to solve tasks with minimal or no task-related examples. Notably, LLMs have been successfully employed…
The capabilities of large language models (LLMs) have been enhanced by training on data that reflects human thought processes, such as the Chain-of-Thought format. However, evidence suggests that the conventional scheme of next-word…
Semantic role labeling (SRL) involves extracting propositions (i.e. predicates and their typed arguments) from natural language sentences. State-of-the-art SRL models rely on powerful encoders (e.g., LSTMs) and do not model non-local…