Singapore

Large Reasoning Models (LRMs) achieve promising results on complex reasoning tasks but remain susceptible to hallucinations. Existing hallucination detection methods based on Large Language Models (LLMs) often focus solely on final answers, overlooking inconsistencies between the answer and reasoning process. This limitation reduces their ability to detect hallucinations during inference. Moreover, training-free approaches lack mechanisms for confidence estimation, resulting in an unquantified detection output. In contrast, training-based methods can provide fine-grained assessments but often neglect the self-correction capability of LRMs, where earlier errors may be corrected in subsequent steps, leading to inaccurate hallucination detection. To address these challenges, we propose \textbf{ConfFuse}, a unified framework that fuses global and local confidence scores for hallucination detection. A Global Hallucination Detection Model (GHDM) is trained using Direct Preference Optimization (DPO) to assess hallucinations at the level of entire reasoning chains, yielding global confidence estimates. Simultaneously, a Process Reward Model (PRM) estimates step-wise confidence scores to capture local logical flaws. A weighted fusion strategy combines the global confidence score with the minimum local score to jointly reflect overall reasoning consistency and local soundness. Experimental evaluations demonstrate that ConfFuse surpasses Qwen3-1.7B and Qwen3-8B by up to 11.86\% and 5.46\% in F1 score on in-distribution datasets, and achieves average improvements of 4.65\% and 2.80\% on out-of-distribution datasets. These results verify the effectiveness and generalizability of the proposed framework.

AAAI 2026

Global-Local Confidence Fusion for Hallucination Detection in Mathematical Reasoning Task

nlp: fact-checking / misinformation detection (nlp focus)

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

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-26 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.<br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

technical paper

Educational recommendation systems have been a fundamental component for alleviating learning disorientation in self-paced learning. While existing studies mainly leverage cognitive theories to guide learning motivation modeling, they critically overlook the role of social influences. Through empirical analysis, we identify social homophily as an additional driver of learning behaviors, i.e., learners tend to adopt resources validated by their social cohort. However, two challenges impede effective social homophily modeling: (1) the absence and sparsity of predefined social relations in online education, and (2) the deep entanglement of social homophily with cognitive homophily in behavioral data. To tackle these challenges, we propose a graph-based framework EdGCL that explicitly disentangles social homophily and cognitive homophily. EdGCL infers implicit social relations from learners' social behaviors and encodes them via a graph transformer, generating social-view representations. Simultaneously, it constructs a heterogeneous learning graph to model cognitive homophily, which is enhanced by a type-aware aggregator and cognitive diagnosis loss. To ensure the semantic distinctiveness of dual-view homophily modeling, a cross-view contrastive disentanglement mechanism is designed to pull intra-view representations closer while pushing inter-view representations away. Evaluation on two real-world educational datasets demonstrates the superior recommendation performance of EdGCL, highlighting the necessity of dual homophily modeling for understanding the motivations behind learning behaviors.

EdGCL: Disentangling Social and Cognitive Homophily in Graph-Based Educational Recommender Systems

Introducing AI concepts in the earliest years of schooling
can help children make sense of intelligent technologies,
yet few resources exist for K–2 classrooms. This paper
presents the design and outcomes of a professional
development (PD) program supporting K–2 teachers as they
explored AI literacy and co-designed unplugged classroom
activities. Grounded in AI4K12’s Five Big Ideas in AI
framework, the PD combined hands-on learning, collaborative
design, and micro-teaching opportunities. Educators created
screen-free, English Language Arts (ELA)-aligned activities
using storytelling, sorting, and embodied play to introduce
AI topics such as machine learning and fairness in
age-appropriate ways. Sample lessons included Train the AI
(pattern recognition), What Happens Next? (equity in
algorithmic decisions), Who Did the Robot Hear? (data
diversity and voice recognition), and Teach the Robot
(guided data-labeling). The PD emphasized integrating AI
into existing K–2 literacy routines, lowering
implementation barriers while supporting vocabulary
development, reasoning, and empathy. Teacher reflections
revealed growing confidence in adapting AI topics for young
learners and highlighted the value of peer collaboration,
clear language, and tactile materials. This work
contributes to the emerging field of early AI education by
demonstrating how co-design and unplugged formats can
empower teachers to introduce foundational AI concepts
through inquiry, play, and literacy-rich (ELA) experiences.

Co-Designing Unplugged Learning Activities with K-2 Teachers for Early AI Literacy Education

Recent advances in AI-generated content (AIGC) have led to the emergence of powerful text-to-video generation models. Despite these successes, evaluating the quality of AIGC-generated videos remains challenging due to limited generalization, lack of temporal awareness, heavy reliance on large-scale annotated datasets, and the lack of effective interaction with generation models. Most current approaches rely on supervised fine-tuning of vision-language models (VLMs), which often require large-scale annotated datasets and tend to decouple understanding and generation. To address these shortcomings, we propose VQ-Insight, a novel reasoning-style VLM framework for AIGC video quality assessment. Our approach features: (1) a progressive video quality learning scheme that combines image quality warm-up, general task-specific temporal learning, and joint optimization with the video generation model; (2) the design of multi-dimension scoring rewards, preference comparison rewards, and temporal modeling rewards to enhance both generalization and specialization in video quality evaluation. Extensive experiments demonstrate that VQ-Insight consistently outperforms state-of-the-art baselines in preference comparison, multi-dimension scoring, and natural video scoring, bringing significant improvements for video generation tasks.

VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning

Inductive knowledge graph completion (KGC) aims to predict missing links involving unseen entities, making it a particularly challenging task for knowledge representation learning. Traditional embedding-based methods often fall short in this setting due to their limited structural reasoning capabilities. Recently, Graph Neural Networks (GNNs) offer a promising alternative by explicitly modeling the graph topology. However, their performance heavily relies on the quality of negative samples during training, which significantly influences the learned representations and generalization ability. To tackle this issue, we propose Adaptive Relation-Aware Negative Sampling (ARNS), a negative sampling approach specifically tailored for GNN-based inductive KGC. It integrates three key strategies: (1) High-quality negatives via Linear WD for discriminative learning, (2) Relation-aware negatives utilizing relation graphs to preserve structural patterns, as well as (3) Adaptive curriculum learning that dynamically adjusts sampling ratios based on performance feedback. Our key innovation lies in a performance-driven adaptation mechanism that monitors training dynamics and modulates negative sample difficulty. This approach starts with easier samples for stability, and progressively introduces challenging negatives. Experiments demonstrate that ARNS outperforms state-of-the-art methods with significant MRR improvements while maintaining training stability. The adaptive design is particularly beneficial in inductive scenarios, where models can infer structural patterns from limited observations.

ARNS: Adaptive Relation-Aware Negative Sampling with Curriculum Learning for Inductive Knowledge Graph Completion

Recent advancements in multi-robot navigation have explored methods that combine Large Language Models (LLMs) for tasks like scene understanding or high-level decision-making. However, these approaches face challenges with high inference latency and potential hallucinations. To address these challenges, we propose a knowledge-driven Reinforcement Learning (RL) framework, GUIDER, that utilizes an LLM in two different offline roles. First, we leverage the LLM as an offline knowledge source. Its expertise is distilled into a compact model, which is applied only when the RL agent is uncertain about its own value estimates and the model itself is confident in its prediction. Additionally, we utilize the LLM as an offline semantic engine. This process translates the LLM's high-level understanding of situational risk into a dynamic adjustment of the RL agent's behavioral style, evolving a function that optimally balances conservative and aggressive actions. We conduct extensive experiments in both terrestrial and maritime settings. Across all maritime scenarios (3–12 robots), GUIDER improves the task success rate and reduces the collision rate significantly compared to the state-of-the-art RL-based multi-robot navigation methods.

Guided Distillation and Risk Adaptive Evolution for Multi-Robot Navigation

Machine Unlearning (MU) aims to remove the influence of specific knowledge from a pretrained model. Existing methods often rely on retained training data to preserve utility; such dependence is impractical due to privacy and scalability constraints. A further complication arises when unlearning is applied to vision-language models (VLMs), where entangled multimodal representations make targeted forgetting especially challenging.
We propose DIET, a principled **retain-data-free unlearning** method for VLMs that addresses these challenges by leveraging the geometry of hyperbolic space. The core idea is to push forget embeddings toward class-mismatched prototypes located at the boundary of the hyperbolic space. In hyperbolic geometry, points near the boundary become infinitely distant from interior points. As a result, moving forget embeddings to the boundary makes their influence on the model asymptotically negligible. To formalize this, we guide the forgetting process using the Busemann function, which quantifies directional distance to the boundary. We further develop an adaptive scheme based on optimal transport that selects mismatched prototypes for each forget embedding, enabling flexible unlearning dynamics.
Extensive experiments on fine-grained datasets such as Flowers102, OxfordPets, and StanfordCars show that DIET achieves an average forget accuracy of 8.06\%, while preserving 69.04\% utility using only 16 samples per concept, significantly outperforming the best retain-free baselines with a **117.5\%** in model utility, 
and showing competitive performance to retain-data baselines with only a **3.79\%** drop

DIET: Machine Unlearning on a Data-Diet

The primary goal of 3D point cloud completion is to reconstruct complete and high-resolution point clouds from incomplete and low-resolution inputs. While some recent approaches have achieved satisfactory completion performance by incorporating additional images, there remains room for improvement in fully exploiting and utilizing the rich geometric relation information contained in parts. To address this challenge, we propose a novel Semantic Guided Part Relation-aware Network (SGPRNet) for Point Cloud Completion. Its core innovation lies in establishing part semantic relations to guide the reconstruction of structurally consistent local geometries. Specifically, we utilize Large Multi-modal Models (LMMs) to automatically generate the specific text of 3D shape, which provides detailed geometric part relations descriptions. Building upon this, we design an Orthogonal Semantic Part Transfer (OSPT) module that learns transferable semantic relations between geometric parts. Subsequently, we develop a Semantic Geometric Relation-aware Transformer (SGRFormer) to progressively refine these semantic features, enhancing point cloud representation and guiding the generation of fine local structures. In addition, we establish a point-text pairs corpus, OmniObject3D-212/34 and Text-ViPC datasets based on existing OmniObject3D and ShapeNet-ViPC datasets, incorporating the specific text. Extensive experimental results demonstrate that our method outperforms existing state-of-the-art completion methods.

Semantic Guided Part Relation-aware Network for Point Cloud Completion

Alignment plays a crucial role in Large Language Models (LLMs) in aligning with human preferences on a specific task/domain. Traditional alignment methods suffer from catastrophic forgetting, where models lose previously learned values when adapting to new preferences or domains. We introduce LifeAlign, a novel framework for lifelong alignment that enables LLMs to maintain consistent human preference alignment across sequential learning tasks without forgetting previously learned values. Our approach consists of two key innovations. First, we propose a focalized preference optimization strategy that aligns LLMs with new preferences while preventing the erosion of alignment acquired from previous tasks. Second, we develop a short-to-long memory consolidation mechanism that merges denoised short-term preference representations into stable long-term memory using intrinsic dimensionality reduction, enabling efficient storage and retrieval of alignment patterns across diverse domains. We evaluate LifeAlign across multiple sequential alignment tasks spanning different domains and preference types. Experimental results demonstrate that our method achieves superior performance in maintaining both preference alignment quality and knowledge retention compared to existing lifelong learning approaches.

LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization

Deep learning has demonstrated expert-level performance in melanoma classification, positioning it as a powerful tool in clinical dermatology. However, model opacity and the lack of interpretability remain critical barriers to clinical adoption, as clinicians often struggle to trust the decision-making processes of black-box models. To address this gap, we present a Cross-Modal Explainable Framework (CMEF) that leverages contrastive learning as the core mechanism for achieving interpretability. Specifically, CMEF maps clinical criteria for melanoma diagnosis—namely Asymmetry, Border, and Color (ABC)—into the Vision Transformer embedding space using dual projection heads, thereby aligning clinical semantics with visual features. The aligned representations are subsequently translated into structured textual explanations via natural language generation, creating a transparent link between raw image data and clinical interpretation. Experiments on public datasets demonstrate 92.79% accuracy and an AUC of 0.961, along with significant improvements across multiple interpretability metrics. Qualitative analyses further show that the spatial arrangement of the learned embeddings aligns with clinicians’ application of the ABC rule, effectively bridging the gap between high-performance classification and clinical trust.

Explainable Melanoma Diagnosis with Contrastive Learning and LLM-based Report Generation

Abstract of T-RO publication: "Robots need to predict and
react to human motions to navigate through a crowd without
collisions. Many existing methods decouple prediction from
planning, which does not account for the interaction
between robot and human motions and can lead to the robot
getting stuck. We propose SICNav, a Model Predictive
Control (MPC) method that jointly solves for robot motion
and predicted crowd motion in closed-loop. We model each
human in the crowd to be following an Optimal Reciprocal
Collision Avoidance (ORCA) scheme and embed that model as a
constraint in the robot's local planner, resulting in a
bilevel nonlinear MPC optimization problem. We use a
KKT-reformulation to cast the bilevel problem as a single
level and use a nonlinear solver to optimize. Our MPC
method can influence pedestrian motion while explicitly
satisfying safety constraints in a single-robot multi-human
environment. We analyze the performance of SICNav in two
simulation environments and indoor experiments with a real
robot to demonstrate safe robot motion that can influence
the surrounding humans. We also validate the trajectory
forecasting performance of ORCA on a human trajectory
dataset."

IEEE Transactions on Robotics (T-RO) Publication: "SICNav:
Safe and Interactive Crowd Navigation Using Model
Predictive Control and Bilevel Optimization"

Downloads

Next from AAAI 2026

EdGCL: Disentangling Social and Cognitive Homophily in Graph-Based Educational Recommender Systems

Similar lecture

Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2026

EdGCL: Disentangling Social and Cognitive Homophily in Graph-Based Educational Recommender Systems

Similar lecture

Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads