Large language models (LLMs) are proficient at generating fluent text with minimal task-specific supervision. However, their ability to generate rationales for knowledge-intensive tasks (KITs) remains under-explored. Generating rationales for KIT solutions, such as commonsense multiple-choice QA, requires external knowledge to support predictions and refute alternate options. In this work, we consider the task of generating retrieval-augmented rationalization of KIT model predictions via external knowledge guidance within a few-shot setting. Surprisingly, crowd-workers preferred LLM-generated rationales over existing crowd-sourced rationales, generated in a similar knowledge-guided setting, on aspects such as factuality, sufficiency, and convincingness. However, fine-grained evaluation of such rationales highlights the need for further improvements in conciseness, novelty, and domain invariance. Additionally, through an expert-sourced study evaluating the reliability of the rationales, we demonstrate that humans’ trust in LLM-generated rationales erodes when communicated faithfully, i.e., without taking model prediction accuracy into account. We find that even instrumenting simple guardrails can be effective for reliable rationalization.

Large language models (LLMs) can label data faster and cheaper than humans for various NLP tasks. Despite their prowess, LLMs may fall short in understanding of complex, sociocultural, or domain-specific context, potentially leading to incorrect annotations. Therefore, we advocate a collaborative approach where humans and LLMs work together to produce reliable and high-quality labels. We present MEGAnno+, a human-LLM collaborative annotation system that offers effective LLM agent and annotation management, convenient and robust LLM annotation, and exploratory verification of LLM labels by humans.

Entity set expansion (ESE) aims at obtaining a more complete set of entities given a textual corpus and a seed set of entities of a concept. Although it is a critical task in many NLP applications, existing benchmarks are limited to well-formed text (e.g., Wikipedia) and well-defined concepts (e.g., countries and diseases). Furthermore, only a small number of predictions are evaluated compared to the actual size of an entity set. A rigorous assessment of ESE methods warrants more comprehensive benchmarks and evaluation. In this paper, we consider user-generated text to understand the generalizability of ESE methods. We develop new benchmarks and propose more rigorous evaluation metrics for assessing the performance of ESE methods. Additionally, we identify phenomena such as non-named entities, multifaceted entities, vague concepts that are more prevalent in user-generated text than well-formed text, and use them to profile ESE methods. We observe that the strong performance of state-of-the-art ESE methods does not generalize well to user-generated text. We conduct comprehensive empirical analysis and draw insights from the findings.

Recently, active learning (AL) methods have been used to effectively fine-tune pre-trained language models for various NLP tasks such as sentiment analysis and document classification. However, given the task of fine-tuning language models, understanding the impact of different aspects on AL methods such as labeling cost, sample acquisition latency, and the diversity of the datasets necessitates a deeper investigation. This paper examines the performance of existing AL methods within a low-resource, interactive labeling setting. We observe that existing methods often underperform in such a setting while exhibiting higher latency and a lack of generalizability. To overcome these challenges, we propose a novel active learning method TYROUGE that employs a hybrid sampling strategy to minimize labeling cost and acquisition latency while providing a framework for adapting to dataset diversity via user guidance. Through our experiments, we observe that compared to SOTA methods, TYROUGE reduces the labeling cost by up to 43% and the acquisition latency by as much as 11X, while achieving comparable accuracy. Finally, we discuss the strengths and weaknesses of TYROUGE by exploring the impact of dataset characteristics.

From tweets to product reviews, text is ubiquitous on the web and often contains valuable information for both enterprises and consumers. However, the online text is generally noisy and incomplete, requiring users to process and analyze the data to extract insights. While there are systems effective for different stages of text analysis, users lack extensible platforms to support interactive text analysis workflows end-to-end. To facilitate integrated text analytics, we introduce LEAM, which aims at combining the strengths of spreadsheets, computational notebooks, and interactive visualizations. LEAM supports interactive analysis via GUI-based interactions and provides a declarative specification language, implemented based on a visual text algebra, to enable user-guided analysis. We evaluate LEAM through two case studies using two popular Kaggle text analytics workflows to understand the strengths and weaknesses of the system.