Association for the Advancement of Artificial Intelligence: AAAI Publications
Not a member yet
26155 research outputs found
Sort by
Translation of User Crochet Patterns to CrochetPARADE Syntax Using Large Language Models
No full textCrochet, with its rich history and popularity, provides a creative and therapeutic outlet for millions across the globe, from many walks of life. However, crochet pattern creation and modification can be challenging for novice users, due to the spatial reasoning and structural understanding of stitches required. CrochetPARADE is a tool created to ease this process through pattern visualisation, but it uses a syntax that differs from standard notation and may not be intuitive to the average crocheter. This study explores the use of Large Language Models (LLMs) to translate user-generated crochet patterns into the CrochetPARADE syntax. The first structured, open-source collection of crochet patterns designed for machine learning applications was created, comprising user-generated patterns and their corresponding CrochetPARADE translations. Various approaches, including baseline, few-shot, and fine-tuning techniques, were evaluated with LLMs. The best results were achieved with fine-tuning DeepSeek-R1-Distill-Llama8b, reaching 74% accuracy, which has the potential to significantly improve the accessibility and ease of crochet pattern creation for users with varying levels of expertise
Teaching Parrots to See Red: Self-Audits of Generative Language Models Overlook Sociotechnical Harms
No full textThe release of ChatGPT as a “low-key research preview” and its viral growth spurred a gold rush among tech companies marketing generative AI (GenAI) as a universal tool. In 2023, the U.S. secured voluntary commitments from top AI developers, including OpenAI, Google, Meta, and Anthropic, to conduct self-audits ensuring model safety before release. However, these models exhibit widespread biases, including by race and gender, unjustly discriminating against users. To inspect this contradiction, we review ten corporate self-audits, finding a notable absence of real-world use cases in sectors like education, creative works, and public policy. Instead, audits focus on thwarting adversarial consumers in hypothetical scenarios and rely on GenAI models to approximate human impacts. This approach places consumers at risk by impairing the mitigation of representational, allocational, and quality-of-service harms. We conclude with recommendations to address audit gaps and protect GenAI consumers
Uncovering Gender Biases in Human-AI Platforms
No full textAs part of my PhD studies, I am focusing on the broad problem of gender related biases in Human-AI systems, making a three-fold contribution to every part of the Responsible AI pipeline-- (i) Adversarial Audits in different human-AI platforms to identify biases against binary & non-binary gender groups, (ii) Novel gender-inclusive datasets and (iii) Low-resource bias mitigation algorithms. The Human-AI systems that I am studying as part of my PhD thesis are-- (a) Face Recognition Systems (FRSs), (b) e-commerce platforms, (c) text-based gender analyzers and (d) Vision Language Models (VLMs). My thesis is divided into three parts-- (i) Adversarial audit of FRSs for binary genders, (ii) Data-centric and model-centric bias mitigation in FRSs for binary genders, and (iii) Audit of non-binary gender bias in other Human-AI systems-- visual-search enabled e-commerce, text-based gender analyzers and VLMs
Intent-Aware Example-Based Explainability
No full textIn this PhD research, I aim to investigate the limitations inherent in current example-based explainability methods, develop solutions to address these deficiencies, and propose a novel direction for research that aligns example-based explainability with user needs and intent. The objectives of this research include: (a) Formalize existing evaluation metrics for local example-based explainability and propose new metrics to assess these methods from user perspectives; (b) Develop a framework for intent-aware local example-based explainability; and (c) Extend the framework for global example-based explainability and generate model-aware, faithful explanations
Alternation-Based Novelty Search
No full textOne key decision for heuristic search algorithms is how to balance exploration and exploitation. In classical planning, the two strongest approaches for this problem are to alternate between different heuristics and to enhance heuristics with novelty measures. The most well-known planner using alternation is LAMA, which cycles between different open-lists that are ordered using different heuristics. The strongest novelty-based algorithms use best-first width search (BFWS), which prefers states that contain previously unseen combinations of atoms. Considerable effort has been put into trying to combine these two approaches, but so far, no combination has been able to significantly improve over the individual planners. In this paper, we explore the simple idea of using BFWS as just another open-list for LAMA. Our results show that adding even the strongest BFWS version to LAMA is detrimental. However, combining only parts of each approach yields a new state-of-the-art agile planner
Automating the Generation of Prompts for LLM-based Action Choice in PDDL Planning
No full textLarge language models (LLMs) have revolutionized a large variety of NLP tasks. An active debate is to what extent they can do reasoning and planning. Prior work has assessed the latter in the specific context of PDDL planning, based on manually converting three PDDL domains into natural language (NL) prompts. Here we automate this conversion step, showing how to leverage an LLM to automatically generate NL prompts from PDDL input. Our automatically generated NL prompts result in similar LLM-planning performance as the previous manually generated ones. Beyond this, the automation enables us to run much larger experiments, providing for the first time a broad evaluation of LLM planning performance in PDDL. Our NL prompts yield better performance than PDDL prompts and simple template-based NL prompts. Compared to symbolic planners, LLM planning lags far behind; but in some domains, our best LLM configuration scales up further than A* using LM-cut
Rack Position Optimization in Large-Scale Heterogeneous Data Centers
No full textAs rapidly growing AI computational demands accelerate the need for new hardware installation and maintenance, this work explores optimal data center resource management by balancing operational efficiency with fault tolerance through strategic rack positioning considering diverse resources and locations. Traditional mixed-integer programming (MIP) approaches often struggle with scalability, while heuristic methods may result in significant sub-optimality. To address these issues, this paper presents a novel two-tier optimization framework using a high-level deep reinforcement learning (DRL) model to guide a low-level gradient-based heuristic for local search. The high-level DRL agent employs Leader Reward for optimal rack type ordering, and the low-level heuristic efficiently maps racks to positions, minimizing movement counts and ensuring fault-tolerant resource distribution. This approach allows scalability to over 100,000 positions and 100 rack types. Our method outperformed the gradient-based heuristic by 7% on average and the MIP solver by over 30% in objective value. It achieved a 100% success rate versus MIP's 97.5% (within a 20-minute limit), completing in just 2 minutes compared to MIP's 1630 minutes (i.e., almost 4 orders of magnitude improvement). Unlike the MIP solver, which showed performance variability under time constraints and high penalties, our algorithm consistently delivered stable, efficient results—an essential feature for large-scale data center management
New Exact Methods for Solving Quadratic Traveling Salesman Problem
No full textThe Quadratic Traveling Salesman Problem (QTSP) is a generalization of the Traveling Salesman Problem (TSP) with important applications in robotics and bioinformatics. The QTSP objective value depends on pairs of consecutive edges in the tour; hence, it is quadratic and generally hard to optimize. While various exact-solving approaches have been explored, many rely on specialized procedures and struggle to scale on large instances. More recently, carefully crafted metaheuristics have demonstrated better primal bounds and scalability, but they cannot provide any guarantees of solution quality nor prove the optimality of any solution. In this work, we propose new exact models for QTSP. We define direct encodings of QTSP in domain-independent dynamic programming (DIDP), constraint programming (CP), mixed integer quadratic programming (MIQP), and mixed integer linear programming (MILP), and compare them with the best-known exact method, a branch and cut (B&C) algorithm, and the state-of-the-art metaheuristic, a hybrid genetic algorithm (HGA). Our experimental results demonstrate that the DIDP model shows better scalability and finds the best feasible solutions on average among all exact solvers, including the B&C algorithm. HGA finds the best feasible solution among all approaches, with DIDP within 15% of the HGA cost on all experimented instances. Also, interestingly, our MILP model with the subtour elimination constraints generally finds better feasible solutions than the B&C algorithm while matching it in proving optimality, suggesting that lazily adding sub-tour elimination cuts is not particularly helpful in QTSP
On the Gains from Using Action Observations in Domain Repair
No full textDesigning a PDDL planning domain is an error-prone task, which can result in unsolvable planning tasks or unexpected plans.
Existing domain repair methods either rely on a complete plan to identify unsatisfied preconditions or operate without any input plan by compiling the flawed planning task into a new planning task with self-repair actions. In contrast, learning approaches often benefit from a range of input observations to infer domain models. In this paper, we extend the self-repair compilation to also accept as input a variable number of action observations. Experimental results show improved domain repair quality and generally strong performance compared to previous domain repair and learning methods
Analyzing Launch Operations Using the Spaceport Throughput Analysis Resource (STAR)
No full textWe describe the development of the Spaceport Throughput Analysis Resource (STAR), which evaluates Kennedy Space Center spaceport launch throughput. STAR integrates simulation and limited rescheduling, using a constraint programming model to check constraints and reschedule events. The outputs of STAR are launch delays, and the constraint violations leading to those delays, that can be used to inform infrastructure investments to reduce future delays. At STAR's core is a constraint program representing a limited horizon scheduling problem used to identify resource constraint violations, and revise schedules in the presence of unexpected events that disrupt the launch schedule. We describe the design and implementation of STAR using illustrative examples, and describe performance results on use cases showing how increased launch rates stress KSC infrastructure