Related papers: Simulating Word Suggestion Usage in Mobile Typing …
UI prototyping often involves iterating and blending elements from examples such as screenshots and sketches, but current tools offer limited support for incorporating these examples. Inspired by the cognitive process of conceptual…
Motivated by the success of powerful while expensive techniques to recognize words in a holistic way, object proposals techniques emerge as an alternative to the traditional text detectors. In this paper we introduce a novel object…
When working on digital devices, people often face distractions that can lead to a decline in productivity and efficiency, as well as negative psychological and emotional impacts. To address this challenge, we introduce a novel Artificial…
Large language models (LLMs) have demonstrated impressive performance on many tasks. However, to achieve optimal performance, specially designed prompting methods are still needed. These methods either rely on task-specific few-shot…
Language Models are extremely susceptible to performance collapse with even small changes to input prompt strings. Libraries such as DSpy (from Stanford NLP) avoid this problem through demonstration-based prompt optimisation. Inspired by…
ChatGPT has achieved remarkable success in natural language understanding. Considering that recommendation is indeed a conversation between users and the system with items as words, which has similar underlying pattern with ChatGPT, we…
Shortcut reasoning is an irrational process of inference, which degrades the robustness of an NLP model. While a number of previous work has tackled the identification of shortcut reasoning, there are still two major limitations: (i) a…
Human-robot interaction requires robots to process language incrementally, adapting their actions in real-time based on evolving speech input. Existing approaches to language-guided robot motion planning typically assume fully specified…
Designing effective prompts can empower LLMs to understand user preferences and provide recommendations with intent comprehension and knowledge utilization capabilities. Nevertheless, recent studies predominantly concentrate on task-wise…
Reading and repeatedly retelling a short story is a common and effective approach to learning the meanings and usages of target words. However, learners often struggle with comprehending, recalling, and retelling the story contexts of these…
Dictation enables efficient text input on mobile devices. However, writing with speech can produce disfluent, wordy, and incoherent text and thus requires heavy post-processing. This paper presents Rambler, an LLM-powered graphical user…
This study addresses the problem of generating an optimised keyboard layout for single-finger typing on a smartphone. It offers Twitter users a tweet-typing experience that requires less effort and time. Bodies of tweet text for 85 popular…
Large language models (LLMs) have demonstrated exceptional performance in planning the use of various functional tools, such as calculators and retrievers, particularly in question-answering tasks. In this paper, we expand the definition of…
This work presents a new task of Text Expansion (TE), which aims to insert fine-grained modifiers into proper locations of the plain text to concretize or vivify human writings. Different from existing insertion-based writing assistance…
Existing debiasing techniques are typically training-based or require access to the model's internals and output distributions, so they are inaccessible to end-users looking to adapt LLM outputs for their particular needs. In this study, we…
It is popular lately to train large language models to be used as chat assistants, but in the conversation between the user and the chat assistant, there are prompts, require multi-turns between the chat assistant and the user. However,…
Large natural language models (such as GPT-3 or T5) demonstrate impressive abilities across a range of general NLP tasks. Here, we show that the knowledge embedded in such models provides a useful inductive bias, not just on traditional NLP…
Developing a novel research idea is hard. It must be distinct enough from prior work to claim a contribution while also building on it. This requires iteratively reviewing literature and refining an idea based on what a researcher reads;…
Tool-Integrated Reasoning (TIR) enables large language models (LLMs) to improve their internal reasoning ability by integrating external tools. However, models employing TIR often display suboptimal behaviors, such as insufficient or…
Autoprompting is the process of automatically selecting optimized prompts for language models, which is gaining popularity due to the rapid development of prompt engineering driven by extensive research in the field of large language models…