As the field of artificial intelligence (AI) and machine learning (ML) continues to prioritize fairness and the concern for historically marginalized communities, the importance of intersectionality in AI research has gained significant recognition. However, few studies provide practical guidance on how researchers can effectively incorporate intersectionality into critical praxis. In response, this paper presents a comprehensive framework grounded in critical reflexivity as intersectional praxis. Operationalizing intersectionality within the AI/DS (Artificial Intelligence/Data Science) pipeline, Quantitative Intersectional Data (QUINTA) is introduced as a methodological paradigm that challenges conventional and superficial research habits, particularly in data-centric processes, to identify and mitigate negative impacts such as the inadvertent marginalization caused by these practices. The framework centers researcher reflexivity to call attention to the AI researchers' power in creating and analyzing AI/DS artifacts through data-centric approaches. To illustrate the effectiveness of QUINTA, we provide a reflexive AI/DS researcher demonstration utilizing the \#metoo movement as a case study. Note: This paper was accepted as a poster presentation at Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO) Conference in 2023.

Large Language Model (LLM)-based agents have emerged as a new paradigm that extends LLMs' capabilities beyond text generation to dynamic interaction with external environments. By integrating reasoning with perception, memory, and tool use, agents are increasingly deployed in diverse domains like web navigation and household robotics. A critical challenge, however, lies in ensuring agent generalizability - the ability to maintain consistent performance across varied instructions, tasks, environments, and domains, especially those beyond agents' fine-tuning data. Despite growing interest, the concept of generalizability in LLM-based agents remains underdefined, and systematic approaches to measure and improve it are lacking. In this survey, we provide the first comprehensive review of generalizability in LLM-based agents. We begin by emphasizing agent generalizability's importance by appealing to stakeholders and clarifying the boundaries of agent generalizability by situating it within a hierarchical domain-task ontology. We then review datasets, evaluation dimensions, and metrics, highlighting their limitations. Next, we categorize methods for improving generalizability into three groups: methods for the backbone LLM, for agent components, and for their interactions. Moreover, we introduce the distinction between generalizable frameworks and generalizable agents and outline how generalizable frameworks can be translated into agent-level generalizability. Finally, we identify critical challenges and future directions, including developing standardized frameworks, variance- and cost-based metrics, and approaches that integrate methodological innovations with architecture-level designs. By synthesizing progress and highlighting opportunities, this survey aims to establish a foundation for principled research on building LLM-based agents that generalize reliably across diverse applications.

Function calling (FC) has emerged as a powerful technique for facilitating large language models (LLMs) to interact with external systems and perform structured tasks. However, the mechanisms through which it influences model behavior remain largely under-explored. Besides, we discover that in addition to the regular usage of FC, this technique can substantially enhance the compliance of LLMs with user instructions. These observations motivate us to leverage causality, a canonical analysis method, to investigate how FC works within LLMs. In particular, we conduct layer-level and token-level causal interventions to dissect FC's impact on the model's internal computational logic when responding to user queries. Our analysis confirms the substantial influence of FC and reveals several in-depth insights into its mechanisms. To further validate our findings, we conduct extensive experiments comparing the effectiveness of FC-based instructions against conventional prompting methods. We focus on enhancing LLM safety robustness, a critical LLM application scenario, and evaluate four mainstream LLMs across two benchmark datasets. The results are striking: FC shows an average performance improvement of around 135% over conventional prompting methods in detecting malicious inputs, demonstrating its promising potential to enhance LLM reliability and capability in practical applications.

Two central capabilities of language models (LMs) are: (i) drawing on prior knowledge about entities, which allows them to answer queries such as "What's the official language of Austria?", and (ii) adapting to new information provided in context, e.g., "Pretend the official language of Austria is Tagalog.", that is pre-pended to the question. In this article, we introduce targeted persuasion score (TPS), designed to quantify how persuasive a given context is to an LM where persuasion is operationalized as the ability of the context to alter the LM's answer to the question. In contrast to evaluating persuasiveness only by inspecting the greedily decoded answer under the model, TPS provides a more fine-grained view of model behavior. Based on the Wasserstein distance, TPS measures how much a context shifts a model's original answer distribution toward a target distribution. Empirically, through a series of experiments, we show that TPS captures a more nuanced notion of persuasiveness than previously proposed metrics.

We explore the applicability of text-to-code to solve real-world problems that are typically solved in natural language, such as legal judgment and medical QA. Unlike previous works, our approach leverages the explicit reasoning provided by program generation. We present ICRAG, a framework that transforms natural language into executable programs through iterative refinement using external knowledge from domain resources and GitHub. Across 13 benchmarks, ICRAG achieves up to 161.1\% relative improvement. We provide a detailed analysis of the generated code and the impact of external knowledge, and we discuss the limitations of applying text-to-code approaches to real-world natural language tasks.

Knowledge of slang is a desirable feature of LLMs in the context of user interaction, as slang often reflects an individual's social identity. Several works on informal language processing have defined and curated benchmarks for tasks such as detection and identification of slang. In this paper, we focus on queer slang. Queer slang can be mistakenly flagged as hate speech or can evoke negative responses from LLMs during user interaction. Research efforts so far have not focused explicitly on queer slang. In particular, detection and processing of queer slang have not been thoroughly evaluated due to the lack of a high-quality annotated benchmark. To address this gap, we curate SLAyiNG, the first dataset containing annotated queer slang derived from subtitles, social media posts, and podcasts, reflecting real-world usage. We describe our data curation process, including the collection of slang terms and definitions, scraping sources for examples that reflect usage of these terms, and our ongoing annotation process. As preliminary results, we calculate inter-annotator agreement for human annotators and OpenAI's model o3-mini, evaluating performance on the task of sense disambiguation. Reaching an average Krippendorff's alpha of 0.746, we argue that state-of-the-art reasoning models can serve as tools for pre-filtering, but the complex and often sensitive nature of queer language data requires expert and community-driven annotation efforts.

We present a comparative analysis of text complexity across domains using scale-free metrics. We quantify linguistic complexity via Heaps' exponent $β$ (vocabulary growth), Taylor's exponent $α$ (word-frequency fluctuation scaling), compression rate $r$ (redundancy), and entropy. Our corpora span three domains: legal documents (statutes, cases, deeds) as a specialized domain, general natural language texts (literature, Wikipedia), and AI-generated (GPT) text. We find that legal texts exhibit slower vocabulary growth (lower $β$) and higher term consistency (higher $α$) than general texts. Within legal domain, statutory codes have the lowest $β$ and highest $α$, reflecting strict drafting conventions, while cases and deeds show higher $β$ and lower $α$. In contrast, GPT-generated text shows the statistics more aligning with general language patterns. These results demonstrate that legal texts exhibit domain-specific structures and complexities, which current generative models do not fully replicate.

Explainability, the capability of an artificial intelligence system (AIS) to explain its outcomes in a manner that is comprehensible to human beings at an acceptable level, has been deemed essential for critical sectors, such as healthcare. Is it really the case? In this perspective, we consider two extreme cases, ``Oracle'' (without explainability) versus ``AI Colleague'' (with explainability) for a thorough analysis. We discuss how the level of automation and explainability of AIS can affect the determination of liability among the medical practitioner/facility and manufacturer of AIS. We argue that explainability plays a crucial role in setting a responsibility framework in healthcare, from a legal standpoint, to shape the behavior of all involved parties and mitigate the risk of potential defensive medicine practices.

Most languages lack sufficient data for large-scale monolingual pretraining, creating a "data wall." Multilingual pretraining helps but is limited by language imbalance and the "curse of multilinguality." An alternative is to translate high-resource text with machine translation (MT), which raises three questions: (1) How does MT-derived data scale with model capacity? (2) Can source-side transformations (e.g., simplifying English with an LLM) improve generalization to native text? (3) How well do models pretrained on MT-derived data adapt when continually trained on limited native text? We investigate these questions by translating English into Indonesian and Tamil--two typologically distant, lower-resource languages--and pretraining GPT-2 models (124M-774M) on native or MT-derived corpora from raw and LLM-simplified English. We evaluate cross-entropy loss on native text, along with accuracy on syntactic probes and downstream tasks. Our results show that (1) MT-pretrained models benefit from scaling; (2) source-side simplification harms generalization to native text; and (3) adapting MT-pretrained models on native text often yields better performance than native-only models, even with less native data. However, tasks requiring cultural nuance (e.g., toxicity detection) demand more exposure to native data.

This work introduces TraceHiding, a scalable, importance-aware machine unlearning framework for mobility trajectory data. Motivated by privacy regulations such as GDPR and CCPA granting users "the right to be forgotten," TraceHiding removes specified user trajectories from trained deep models without full retraining. It combines a hierarchical data-driven importance scoring scheme with teacher-student distillation. Importance scores--computed at token, trajectory, and user levels from statistical properties (coverage diversity, entropy, length)--quantify each training sample's impact, enabling targeted forgetting of high-impact data while preserving common patterns. The student model retains knowledge on remaining data and unlearns targeted trajectories through an importance-weighted loss that amplifies forgetting signals for unique samples and attenuates them for frequent ones. We validate on Trajectory--User Linking (TUL) tasks across three real-world higher-order mobility datasets (HO-Rome, HO-Geolife, HO-NYC) and multiple architectures (GRU, LSTM, BERT, ModernBERT, GCN-TULHOR), against strong unlearning baselines including SCRUB, NegGrad, NegGrad+, Bad-T, and Finetuning. Experiments under uniform and targeted user deletion show TraceHiding, especially its entropy-based variant, achieves superior unlearning accuracy, competitive membership inference attack (MIA) resilience, and up to 40\times speedup over retraining with minimal test accuracy loss. Results highlight robustness to adversarial deletion of high-information users and consistent performance across models. To our knowledge, this is the first systematic study of machine unlearning for trajectory data, providing a reproducible pipeline with public code and preprocessing tools.