United States

This paper presents an explainable AI (XAI) education tool designed for K-12 classrooms, particularly for students aged 11-16. The tool was designed for interventions on the fundamental processes behind social media platforms, focusing on four AI- and data-driven core concepts: data collection, user profiling, engagement metrics, and recommendation algorithms. An Instagram-like interface and a monitoring tool for explaining the data-driven processes make these complex ideas accessible and engaging for young learners. The tool provides hands-on experiments and real-time visualizations, illustrating how user actions influence their personal experience on the platform as well as the experience of others. This approach seeks to enhance learners&#39; data agency, AI literacy, and sensitivity to AI ethics. The paper includes a case example from 12 two-hour test sessions involving 209 children, using learning analytics to demonstrate how they navigated their social media feeds and the browsing patterns that emerged.

AAAI 2025

An XAI Social Media Platform for Teaching K-12 Students AI-Driven Profiling, Clustering, and Engagement-Based Recommending

This paper presents an explainable AI (XAI) education tool designed for K-12 classrooms, particularly for students aged 11-16. The tool was designed for interventions on the fundamental processes behind social media platforms, focusing on four AI- and data-driven core concepts: data collection, user profiling, engagement metrics, and recommendation algorithms. An Instagram-like interface and a monitoring tool for explaining the data-driven processes make these complex ideas accessible and engaging for young learners. The tool provides hands-on experiments and real-time visualizations, illustrating how user actions influence their personal experience on the platform as well as the experience of others. This approach seeks to enhance learners' data agency, AI literacy, and sensitivity to AI ethics. The paper includes a case example from 12 two-hour test sessions involving 209 children, using learning analytics to demonstrate how they navigated their social media feeds and the browsing patterns that emerged.

technical paper

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



With rapid advances, generative large language models (LLMs) dominate various Natural Language Processing (NLP) tasks from understanding to reasoning. Yet, language models' inherent vulnerabilities may be exacerbated due to increased accessibility and unrestricted model training on massive textual data from the Internet. A malicious adversary may publish poisoned data online and conduct backdoor attacks on the victim LLMs pre-trained on the poisoned data. Backdoored LLMs behave innocuously for normal queries and generate harmful responses when the backdoor trigger is activated. Despite significant efforts paid to LLMs' safety issues, LLMs are still struggling against backdoor attacks. As Anthropic recently revealed, existing safety training strategies, including supervised fine-tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), fail to revoke the backdoors once the LLM is backdoored during the pre-training stage. In this paper, we present Simulate and Eliminate (SANDE) to erase the undesired backdoored mappings for generative LLMs. We initially propose Overwrite Supervised Fine-tuning (OSFT) for effective backdoor removal when the trigger is known. Then, to handle the scenarios where the trigger patterns are unknown, we integrate OSFT into our two-stage framework, SANDE. Unlike previous works that center on the identification of backdoors, our safety-enhanced LLMs are able to behave normally even when the exact triggers are activated. We conduct comprehensive experiments to show that our proposed SANDE is effective against backdoor attacks while bringing minimal harm to LLMs' powerful capability without any additional access to unbackdoored clean models. We will release the reproducible code.

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models

Lately, the practice of utilizing task-specific fine-tuning has been implemented to improve the performance of large language models (LLM) in subsequent tasks. Through the integration of diverse LLMs, the overall competency of LLMs is significantly boosted. Nevertheless, traditional ensemble methods are notably memory-intensive, necessitating the simultaneous loading of all specialized models into GPU memory. To address the inefficiency, model merging strategies have emerged, merging all LLMs into one model to reduce the memory footprint during inference. Despite these advances, model merging often leads to parameter conflicts and performance decline as the number of experts increases. Previous methods to mitigate these conflicts include post-pruning and partial merging. However, both approaches have limitations, particularly in terms of performance and storage efficiency when merged experts increase. To address these challenges, we introduce Channel Merging, a novel strategy designed to minimize parameter conflicts while enhancing storage efficiency. This method initially clusters and merges channel parameters based on their similarity to form several groups offline. By ensuring that only highly similar parameters are merged within each group, it significantly reduces parameter conflicts. During inference, we can instantly look up the expert parameters from the merged groups, preserving specialized knowledge. Our experiments demonstrate that Channel Merging consistently delivers high performance, matching unmerged models in tasks like English and Chinese reasoning, mathematical reasoning, and code generation. Moreover, it obtains results comparable to model ensemble with just 53% parameters when used with a task-specific router.

Channel Merging: Preserving Specialization for Merged Experts

Among various branches of offline Reinforcement Learning (RL) methods, Goal-Conditioned Supervised Learning (GCSL) that formulates offline RL problem as a sequential modeling task, has gained increasing popularities as it bypasses the notoriously difficult credit assignment challenge of value learning in traditional RL paradigm. Sequential modeling, however, requires capturing accurate dynamics across long horizons within decision trajectories to ensure reasonable policy rollouts. To meet this requirement, leveraging expressive models with large amount of parameters seems become a default choice for researchers, which, however, comes with significantly increased computational cost and inference latency. Contradicting yet promising, we reveal that lightweight models, even a simple shallow 2-layer MLP, can effectively enjoy accurate dynamics consistency and significantly reduce the sequential modeling errors against large expressive models by adopting a simple recursive planning manner: recursively planning coarse-grained future subgoals based on current and target information, and then executes actions with an outcome-conditioned policy learned from data relabeled with these subgoals, which we term as . Simple yet effective, RSP enjoys significant efficiency improvements thanks to its lightweight models, and substantially outperforms previous methods and achieves SOTA performances on the D4RL benchmark, especially in multi-stage long-horizon tasks.

Are Expressive Models Truly Necessary for Offline RL?

Human cognition can leverage fundamental conceptual knowledge, like geometry and kinematic ones, to appropriately perceive, comprehend and interact with novel objects. Motivated by this finding, we aim to endow machine intelligence with an analogous capability through performing at the conceptual level, in order to understand and then interact with articulated objects, especially for those in novel categories, which is challenging due to the intricate geometric structures and diverse joint types of articulated objects. To achieve this goal, we propose Analytic Ontology Template (AOT), a parameterized and differentiable program description of generalized conceptual ontologies. A baseline approach called AOTNet driven by AOTs is designed accordingly to equip intelligent agents with these generalized concepts, and then empower the agents to effectively discover the conceptual knowledge on the structure and affordance of articulated objects. The AOT-driven approach yields benefits in three key perspectives: i) enabling concept-level understanding of articulated objects without relying on any real training data, ii) providing analytic structure information, and iii) introducing rich affordance information indicating proper ways of interaction. We conduct exhaustive experiments and the results demonstrate the superiority of our approach in understanding and the interacting with articulated objects. More details, additional analysis and comprehensive discussions are provided in the supplementary material. Our code including the AOTs will be made publicly available to facilitate better adoption of our ideas within the community.

Discovering Conceptual Knowledge with Analytic Ontology Templates for Articulated Objects

Expressing negative conditions is a crucial feature of query languages for knowledge bases (KBs). Answering such queries over ontological KBs, however, is a very challenging task that becomes undecidable even for lightweight Description Logic (DL) ontologies. Such negative results hold even for Conjunctive Queries (CQs) equipped with basic forms negative conditions such as the the so-called "safe" negation or inequality atoms. One ontology language that is seemingly unaffected by these results is (the DL counterpart of) RDFS even if augmented it with disjointness axioms. Answering CQs with inequality atoms over such ontologies is known to be $\Pi^p_2$-complete, if the number of inequality atoms is unbounded, and NP-complete if we limit this number to one. Notably, these results leave open the cases of CQs with a fixed number greater than two of inequality atoms. Additionally, such a thorough analysis is missing for CQs with with safe negation.

In this paper, we embark in a refined analysis of the combined complexity of answering CQs with inequality atoms and safe negation over RDFS ontologies augmented with disjointness axioms. Firstly, we provide a unified $\Pi^p_2$ query answering algorithm for the general problem. Secondly, we confirm the generally held conjecture according to which answering CQs with two inequality atoms over such ontologies is already $\Pi^p_2$-hard. This result closes an important gap in the current literature and has an impact on the widely influential problem of query containment. We make such connection clear in the paper. Lastly, for CQs with safe negation, we prove a behavior similar to that of CQs with inequality atoms. Specifically, we show that answering CQs with at most one negative atom can be done in NP, while allowing at most two negative atoms is sufficient to obtain $\Pi^p_2$-hardness. To the best of our knowledge, this is the first result of this kind in the literature shedding light on the behavior of a fundamental query language.

Answering Conjunctive Queries with Safe Negation and Inequalities over RDFS Knowledge Bases

This paper investigates how hallucination rates in Large Language Models (LLMs) may be controlled via a symbolic data generation framework, and explores a fundamental relationship between the rate of certain mathematical errors and interventions. Specifically, we systematically generate data for a derivation generation task, and apply targeted interventions on prompts to perturb aspects such as the surface forms of symbols, equational tree structures, and mathematical context, and evaluate the effect of prompt interventions across a range of LLMs including fine-tuned T5 models, GPT, and others. Experiments suggest that T5-Large can outperform the few-shot performance of GPT-4T on various evaluation sets generated via the framework, however, an extensive evaluation based on human analysis, template-based error detection, and various text generation metrics, reveals fine-tuned model weaknesses beyond what the reference-based metrics singularly describe. We use these results to tie characteristic distributional footprints of interventions to the human evaluation of LLM derivation quality, potentially leading to significant control over fine-grained mathematical capabilities of language models with respect to specific types of errors.

Controlling Equational Reasoning in Large Language Models with Prompt Interventions

Human–Computer Interaction for AI Systems Design is an eight-week short online course aimed at professional students. It is part of an online course platform called Cambridge Advance Online, which is a joint effort between Cambridge University Press & Assessment and the University of Cambridge. This course launched in July 2023 amidst a massive increase in interest in AI and its applications, and quickly became one of the platform's highest-enrolling courses, attracting about 50 students per quarterly course run. To date, more than 200 students have completed the course, and more than 90 percent have rated their experience `good' or `excellent'. This paper reports on our experiences in designing and teaching this course.

Human-Computer Interaction for AI Systems Design: Reflections on an Online Course on Human-AI Interaction for Professionals

Responsible AI (RAI) encompasses the science and practice of ensuring that AI design, development, and use are socially sustainable--—maximizing the benefits of technology while mitigating its risks. Industry practitioners play a crucial role in achieving the objectives of RAI, yet there is a persistent a shortage of consolidated educational resources and effective methods for teaching RAI to practitioners.

In this paper, we present a stakeholder-first educational approach using interactive case studies to foster organizational and practitioner-level engagement and enhance learning about RAI. We detail our partnership with Meta, a global technology company, to co-develop and deliver RAI workshops to a diverse company audience. Assessment results show that participants found the workshops engaging and reported an improved understanding of RAI principles, along with increased motivation to apply them in their work.

Using Case Studies to Teach Responsible AI to Industry Practitioners

The media are agog with claims that recent advances in AI put artificial general intelligence (AGI) within reach. Is this true?  If so, is that a good thing? Alan Turing predicted that AGI would result in the machines taking control. Turing was right to express concern but wrong to think that doom is inevitable. Yet the question of whether superior AI systems can really benefit humanity remains unanswered. It may be that they can do so only by their absence.

Can AI Benefit Humanity?

Over the past few years, Artificial Intelligence has bounded into the mainstream of society.  Remarkable technical achievements in the use of Deep Learning and  Large Language Models have given rise to expectations and hype regarding the possibility of achieving artificial general intelligence, as well as general concerns over the potential deleterious consequences of emerging AI technologies and how to ensure their responsible use. In this panel we engage four Past AAAI Presidents to discuss their views on questions relating to the current state and future of AI research, including such topics as important emerging application areas, current technical challenges, the eventual prospects for achieving artificial general intelligence, and potential AI risks and solutions.

Premium content

Next from AAAI 2025

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES