Related papers: From Brittle to Robust: Improving LLM Annotations …
Large language models (LLMs) demonstrate exceptional instruct-following ability to complete various downstream tasks. Although this impressive ability makes LLMs flexible task solvers, their performance in solving tasks also heavily relies…
Large language models (LLMs) have enhanced our ability to rapidly analyze and classify unstructured natural language data. However, concerns regarding cost, network limitations, and security constraints have posed challenges for their…
Large language models (LLMs) have been garnering increasing attention in the recommendation community. Some studies have observed that LLMs, when fine-tuned by the cross-entropy (CE) loss with a full softmax, could achieve…
Large language models (LLMs) have demonstrated significant capability to generalize across a large number of NLP tasks. For industry applications, it is imperative to assess the performance of the LLM on unlabeled production data from time…
Large language models (LLMs) offer significant potential to accelerate systematic literature reviews (SLRs), yet current approaches often rely on brittle, manually crafted prompts that compromise reliability and reproducibility. This…
This paper explores the challenges of test-time scaling of large language models (LLMs), regarding both the data and inference efficiency. We highlight the diversity of multi-lingual reasoning based on our pilot studies, and then introduce…
Large language models (LLMs) have demonstrated remarkable performance, yet their diverse strengths and weaknesses prevent any single LLM from achieving dominance across all tasks. Ensembling multiple LLMs is a promising approach to generate…
We propose a novel zero-shot document ranking approach based on Large Language Models (LLMs): the Setwise prompting approach. Our approach complements existing prompting approaches for LLM-based zero-shot ranking: Pointwise, Pairwise, and…
Automatic speech recognition (ASR) models rely on high-quality transcribed data for effective training. Generating pseudo-labels for large unlabeled audio datasets often relies on complex pipelines that combine multiple ASR outputs through…
While modern Requirements Engineering (RE) heavily relies on natural language processing and Machine Learning (ML) techniques, their effectiveness is limited by the scarcity of high-quality datasets. This paper introduces Synthline, a…
Large language models (LLMs) have been widely adopted for synthetic data generation, significantly reducing annotation costs. However, most existing studies treat synthesis as a set of isolated tasks and overlook a more fundamental…
As Large Language Models (LLMs) grow increasingly adept at managing complex tasks, the evaluation set must keep pace with these advancements to ensure it remains sufficiently discriminative. Item Discrimination (ID) theory, which is widely…
Recent advances in large pre-trained language models (PLMs) lead to impressive gains in natural language understanding (NLU) tasks with task-specific fine-tuning. However, directly fine-tuning PLMs heavily relies on sufficient labeled…
Multiple-choice question (MCQ) benchmarks have been a standard evaluation practice for measuring LLMs' ability to reason and answer knowledge-based questions. Through a synthetic NonsenseQA benchmark, we observe that different LLMs exhibit…
Industrial process control demands policies that are interpretable and auditable, requirements that black-box neural policies struggle to meet. We study an LLM-driven heuristic synthesis framework for hot steel rolling, in which a language…
The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples. However, they require enormous computational resources to be deployed. Alternatively,…
Large language models (LLMs) have shown impressive performance on general-purpose tasks, yet adapting them to specific domains remains challenging due to the scarcity of high-quality domain data. Existing data synthesis tools often struggle…
Despite growing interest in using large language models (LLMs) to automate annotation, their effectiveness in complex, nuanced, and multi-dimensional labelling tasks remains relatively underexplored. This study focuses on annotation for the…
The advent of Large Language Models (LLMs) has significantly advanced the field of automated code generation. LLMs rely on large and diverse datasets to learn syntax, semantics, and usage patterns of programming languages. For low-resource…
Many structured prediction and reasoning tasks can be framed as program synthesis problems, where the goal is to generate a program in a domain-specific language (DSL) that transforms input data into the desired output. Unfortunately,…