Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant

Since the explosion in popularity of ChatGPT, large language models (LLMs) have continued to impact our everyday lives. Equipped with external tools that are designed for a specific purpose (e.g., for flight booking or an alarm clock), LLM agents exercise an increasing capability to assist humans in their daily work. Although LLM agents have shown a promising blueprint as daily assistants, there is a limited understanding of how they can provide daily assistance based on planning and sequential decision making capabilities. We draw inspiration from recent work that has highlighted the value of 'LLM-modulo' setups in conjunction with humans-in-the-loop for planning tasks. We conducted an empirical study (N = 248) of LLM agents as daily assistants in six commonly occurring tasks with different levels of risk typically associated with them (e.g., flight ticket booking and credit card payments). To ensure user agency and control over the LLM agent, we adopted LLM agents in a plan-then-execute manner, wherein the agents conducted step-wise planning and step-by-step execution in a simulation environment. We analyzed how user involvement at each stage affects their trust and collaborative team performance. Our findings demonstrate that LLM agents can be a double-edged sword -- (1) they can work well when a high-quality plan and necessary user involvement in execution are available, and (2) users can easily mistrust the LLM agents with plans that seem plausible. We synthesized key insights for using LLM agents as daily assistants to calibrate user trust and achieve better overall task outcomes. Our work has important implications for the future design of daily assistants and human-AI collaboration with LLM agents.

SubData: A Python Library to Collect and Combine Datasets for Evaluating LLM Alignment on Downstream Tasks

With the release of ever more capable large language models (LLMs), researchers in NLP and related disciplines have started to explore the usability of LLMs for a wide variety of different annotation tasks. Very recently, a lot of this attention has shifted to tasks that are subjective in nature. Given that the latest generations of LLMs have digested and encoded extensive knowledge about different human subpopulations and individuals, the hope is that these models can be trained, tuned or prompted to align with a wide range of different human perspectives. While researchers already evaluate the success of this alignment via surveys and tests, there is a lack of resources to evaluate the alignment on what oftentimes matters the most in NLP; the actual downstream tasks. To fill this gap we present SubData, a Python library that offers researchers working on topics related to subjectivity in annotation tasks a convenient way of collecting, combining and using a range of suitable datasets.

Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas

The analysis of political biases in large language models (LLMs) has primarily examined these systems as single entities with fixed viewpoints. While various methods exist for measuring such biases, the impact of persona-based prompting on LLMs' political orientation remains unexplored. In this work we leverage PersonaHub, a collection of synthetic persona descriptions, to map the political distribution of persona-based prompted LLMs using the Political Compass Test (PCT). We then examine whether these initial compass distributions can be manipulated through explicit ideological prompting towards diametrically opposed political orientations: right-authoritarian and left-libertarian. Our experiments reveal that synthetic personas predominantly cluster in the left-libertarian quadrant, with models demonstrating varying degrees of responsiveness when prompted with explicit ideological descriptors. While all models demonstrate significant shifts towards right-authoritarian positions, they exhibit more limited shifts towards left-libertarian positions, suggesting an asymmetric response to ideological manipulation that may reflect inherent biases in model training.

Perception of Visual Content: Differences Between Humans and Foundation Models

Human-annotated content is often used to train machine learning (ML) models. However, recently, language and multi-modal foundational models have been used to replace and scale-up human annotator's efforts. This study compares human-generated and ML-generated annotations of images representing diverse socio-economic contexts. We aim to understand differences in perception and identify potential biases in content interpretation. Our dataset comprises images of people from various geographical regions and income levels washing their hands. We compare human and ML-generated annotations semantically and evaluate their impact on predictive models. Our results show low similarity between human and machine annotations from a low-level perspective, i.e., types of words that appear and sentence structures, but are alike in how similar or dissimilar they perceive images across different regions. Additionally, human annotations resulted in best overall and most balanced region classification performance on the class level, while ML Objects and ML Captions performed best for income regression. Humans and machines' similarity in their lack of bias when perceiving images highlights how they are more alike than what was initially perceived. The superior and fairer performance of using human annotations for region classification and machine annotations for income regression show how important the quality of the images and the discriminative features in the annotations are.

Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges

Natural Language Processing is revolutionizing the way legal professionals and laypersons operate in the legal field. The considerable potential for Natural Language Processing in the legal sector, especially in developing computational tools for various legal processes, has captured the interest of researchers for years. This survey follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework, reviewing 148 studies, with a final selection of 127 after manual filtering. It explores foundational concepts related to Natural Language Processing in the legal domain, illustrating the unique aspects and challenges of processing legal texts, such as extensive document length, complex language, and limited open legal datasets. We provide an overview of Natural Language Processing tasks specific to legal text, such as Legal Document Summarization, legal Named Entity Recognition, Legal Question Answering, Legal Text Classification, and Legal Judgment Prediction. In the section on legal Language Models, we analyze both developed Language Models and approaches for adapting general Language Models to the legal domain. Additionally, we identify 15 Open Research Challenges, including bias in Artificial Intelligence applications, the need for more robust and interpretable models, and improving explainability to handle the complexities of legal language and reasoning.

Optimizing LLMs with Direct Preferences: A Data Efficiency Perspective

Aligning the output of Large Language Models (LLMs) with human preferences (e.g., by means of reinforcement learning with human feedback, or RLHF) is essential for ensuring their effectiveness in real-world scenarios. Despite significant advancements in LLM alignment techniques, the impact of different type of preference data on model performance has yet to be systematically explored. In this study, we investigate the scalability, data efficiency, and effectiveness of Direct Preference Optimization (DPO) in fine-tuning pre-trained LLMs, aiming to reduce their dependency on extensive amounts of preference data, which is expensive to collect. We (1) systematically compare the performance of models fine-tuned with varying percentages of a combined preference judgement dataset to define the improvement curve of DPO and assess its effectiveness in data-constrained environments; and (2) provide insights for the development of an optimal approach for selective preference data usage. Our study reveals that increasing the amount of data used for training generally enhances and stabilizes model performance. Moreover, the use of a combination of diverse datasets significantly improves model effectiveness. Furthermore, when models are trained separately using different types of prompts, models trained with conversational prompts outperformed those trained with question answering prompts.

Personas with Attitudes: Controlling LLMs for Diverse Data Annotation

We present a novel approach for enhancing diversity and control in data annotation tasks by personalizing large language models (LLMs). We investigate the impact of injecting diverse persona descriptions into LLM prompts across two studies, exploring whether personas increase annotation diversity and whether the impacts of individual personas on the resulting annotations are consistent and controllable. Our results show that persona-prompted LLMs produce more diverse annotations than LLMs prompted without personas and that these effects are both controllable and repeatable, making our approach a suitable tool for improving data annotation in subjective NLP tasks like toxicity detection.

Fairness without Sensitive Attributes via Knowledge Sharing

While model fairness improvement has been explored previously, existing methods invariably rely on adjusting explicit sensitive attribute values in order to improve model fairness in downstream tasks. However, we observe a trend in which sensitive demographic information becomes inaccessible as public concerns around data privacy grow. In this paper, we propose a confidence-based hierarchical classifier structure called "Reckoner" for reliable fair model learning under the assumption of missing sensitive attributes. We first present results showing that if the dataset contains biased labels or other hidden biases, classifiers significantly increase the bias gap across different demographic groups in the subset with higher prediction confidence. Inspired by these findings, we devised a dual-model system in which a version of the model initialised with a high-confidence data subset learns from a version of the model initialised with a low-confidence data subset, enabling it to avoid biased predictions. Our experimental results show that Reckoner consistently outperforms state-of-the-art baselines in COMPAS dataset and New Adult dataset, considering both accuracy and fairness metrics.

Hate Speech Detection with Generalizable Target-aware Fairness

To counter the side effect brought by the proliferation of social media platforms, hate speech detection (HSD) plays a vital role in halting the dissemination of toxic online posts at an early stage. However, given the ubiquitous topical communities on social media, a trained HSD classifier easily becomes biased towards specific targeted groups (e.g., female and black people), where a high rate of false positive/negative results can significantly impair public trust in the fairness of content moderation mechanisms, and eventually harm the diversity of online society. Although existing fairness-aware HSD methods can smooth out some discrepancies across targeted groups, they are mostly specific to a narrow selection of targets that are assumed to be known and fixed. This inevitably prevents those methods from generalizing to real-world use cases where new targeted groups constantly emerge over time. To tackle this defect, we propose Generalizable target-aware Fairness (GetFair), a new method for fairly classifying each post that contains diverse and even unseen targets during inference. To remove the HSD classifier's spurious dependence on target-related features, GetFair trains a series of filter functions in an adversarial pipeline, so as to deceive the discriminator that recovers the targeted group from filtered post embeddings. To maintain scalability and generalizability, we innovatively parameterize all filter functions via a hypernetwork that is regularized by the semantic affinity among targets. Taking a target's pretrained word embedding as input, the hypernetwork generates the weights used by each target-specific filter on-the-fly without storing dedicated filter parameters. Finally, comparative experiments on two HSD datasets have shown advantageous performance of GetFair on out-of-sample targets.

Estimating Gender Completeness in Wikipedia

Gender imbalance in Wikipedia content is a known challenge which the editor community is actively addressing. The aim of this paper is to provide the Wikipedia community with instruments to estimate the magnitude of the problem for different entity types (also known as classes) in Wikipedia. To this end, we apply class completeness estimation methods based on the gender attribute. Our results show not only which gender for different sub-classes of Person is more prevalent in Wikipedia, but also an idea of how complete the coverage is for difference genders and sub-classes of Person.