Singapore

Explanation fidelity, which measures how accurately an explanation reflects a model’s true reasoning, remains critically underexplored in recommender systems. We introduce SPINRec (Stochastic Path Integration for Neural Recommender Explanations), a model-agnostic explanation method that adapts path-integration techniques to the sparse and implicit nature of recommendation data. To address the limitations of prior approaches, SPINRecemploys a stochastic baseline sampling strategy. Instead of integrating from a fixed or unrealistic baseline, it samples multiple plausible user profiles from the empirical data distribution and selects the most faithful attribution path. This design accounts for the importance of both observed and unobserved interactions in modern recommenders, resulting in more stable, accurate, and personalized explanations. We conduct the most comprehensive fidelity evaluation to date in this domain. Our experiments span three models (MF, VAE, NCF), three datasets (ML1M, Yahoo! Music, Pinterest), and a suite of counterfactual metrics, including AUC-based perturbation curves and fixed-length diagnostics. SPINRec consistently outperforms strong baselines such as SHAP, LIME, FIA, and LXR across all evaluation settings. These results establish a new benchmark for faithful explainability in recommendation. Code and evaluation tools will be released publicly to support reproducibility and future research.

AAAI 2026

Fidelity-Aware Recommendation Explanations via Stochastic Path Integration

interpretability & explainability recommender systems deep learning algorithms

### Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

NAACL 2025

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

technical paper

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.

To access this event page, you need to log in with the **email address you registered with**. 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.

Weight Averaging (WA) has emerged as a powerful technique for enhancing generalization by promoting convergence to a flat loss landscape, which correlates with stronger out-of-distribution performance. However, applying WA directly to multi-modal domain generalization (MMDG) is challenging: differences in optimization speed across modalities lead WA to overfit to faster-converging ones in early stages, suppressing the contribution of slower yet complementary modalities, thereby hindering effective modality fusion and skewing the loss surface toward sharper, less generalizable minima.
To address this issue, we propose MBCD, a unified collaborative distillation framework that retains WA's flatness-inducing advantages while overcoming its shortcomings in multi-modal contexts. MBCD begins with adaptive modality dropout in the student model to curb early-stage bias toward dominant modalities. A gradient consistency constraint then aligns learning signals between uni-modal branches and the fused representation, encouraging coordinated and smoother optimization. Finally, a WA-based teacher conducts cross-modal distillation by transferring fused knowledge to each uni-modal branch, which strengthens cross-modal interactions and steer convergence toward flatter solutions. 
Extensive experiments on MMDG benchmarks show that MBCD consistently outperforms existing methods, achieving superior accuracy and robustness across diverse unseen domains.

Modality-Balanced Collaborative Distillation for Multi-Modal Domain Generalization

The proliferation of high-quality text from Large Language Models (LLMs) demands reliable and efficient detection methods. While existing training-free approaches show promise, they often rely on surface-level statistics and overlook fundamental signal properties of the text generation process. In this work, we reframe detection as a signal processing problem, introducing a novel paradigm that analyzes the sequence of token log-probabilities in the frequency domain. By systematically analyzing the signal's spectral properties using the global Discrete Fourier Transform (DFT) and the local Short-Time Fourier Transform (STFT), we find that human-written text consistently exhibits significantly higher spectral energy. This higher energy reflects the larger-amplitude fluctuations inherent in human writing compared to the suppressed dynamics of LLM-generated text.
Based on this key insight, we construct SpecDetect, a detector built on a single, robust feature from the global DFT: DFT total energy. We also propose an enhanced version, SpecDetect++, which incorporates a sampling discrepancy mechanism to further boost robustness. Extensive experiments demonstrate that our approach outperforms the state-of-the-art model while running in nearly half the time. Our work introduces a new, efficient, and interpretable pathway for LLM-generated text detection, showing that classical signal processing techniques offer a surprisingly powerful solution to this modern challenge. Our code is provided in the supplementary material.

SpecDetect: Simple, Fast, and Training-Free Detection of LLM-Generated Text via Spectral Analysis

Satellite-acquired optical remote sensing imagery is extensively applied in time-critical applications like traffic surveillance and evaluation of natural disasters. However, clouds, as a common atmospheric phenomenon, frequently obscure observation. 
Current approaches aim to restore visibility in cloud-obscured regions, yet they typically fall short in the presence of dense cloud cover, which are exceedingly prevalent in remote sensing imagery. Alternative approaches rely on the satellite revisit cycle, frequently surpassing ten days, a duration impractical for genuine application scenarios due to target changes and bandwidth limitations.
To address these issues, this paper proposes SCo-Cloud,
a novel satellite constellation collaboration framework for cloud-aware onboard-computed imaging and transmission, 
which consists of Center-Sat and Edge-Sats.
We propose onboard thin cloud removal and re-imaging region location models to locate the impact of clouds.
We further design a novel multi-satellite scheduling strategy to eliminate clouds.
The models above are integrated within the Center-Sat, with the nearby Edge-Sats collaborating in tandem to execute re-imaging assignments.
Furthermore, to facilitate in-depth research, we have meticulously developed a cloud-covered target detection dataset.
Comprehensive experiments have conclusively demonstrated that SCo-Cloud effectively surpasses the limitations inherent in current approaches, providing accurate and timely responses within the domain of Earth observation.

SCo-Cloud: Satellite Constellation Collaboration for Cloud-Aware Onboard-Computed Imaging and Transmission

Event co-occurrences have been proven effective for event argument extraction (EAE) in previous studies; 
however, few have considered intra- and inter-event role correlations. Since role varies among different event types, event structure heterogeneity and overlap pose significant challenges to EAE. To address this issue, we propose a Role Correlation Structure-Enhanced model for Multi-Event Argument Extraction (RoSE), capable of capturing both heterogeneity and overlap of event structures through modeling role correlations. The proposed RoSE model employs a joint context-prompts input, role-centric graph-guided encoder (RoGE), and role-specific information fusion (RoIF). The RoGE is designed to enhance the intra- and inter-event role correlation between prompts and their corresponding event contexts. The RoIF module utilizes intra-event role information to improve multi-event arguments extraction.
Extensive experiments on four widely-used benchmarks (RAMS, WikiEvents, MLEE, and ACE05) demonstrate that our proposed approach achieves state-of-the-art performance, validating the effectiveness of incorporating both intra- and inter-event role correlations.
Our code is available here.

RoSE: A Role Correlation Structure-Enhanced Model for Multi-Event Argument Extraction

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding and generation by integrating visual and textual data. However, these models frequently exhibit object hallucination problems: generating outputs that are inconsistent with the input image. Existing improved methods for mitigating hallucinations still suffer from two key limitations: dynamic approaches based on logits or attention mechanisms risk suppressing valuable linguistic priors, whereas static methods that employ fixed intervention vectors lack the flexibility to adapt to diverse images and questions. To address these issues, we propose RFI (Rectified Flow Intervention), a novel approach that harnesses the linear trajectory design of rectified flow for input-specific adaptation and employs gradient correction to ensure coherent generation, effectively combining the adaptability of dynamic methods with the stability of static ones. RFI dynamically predicts latent-space intervention vectors while requiring only a single forward pass in LVLMs per question, achieving computational efficiency (1.09x latency overhead for 100 new tokens). Extensive experiments show RFI significantly reduces hallucinations, achieving superior performance compared to existing advanced methods, highlighting its effectiveness as a lightweight plug-and-play method for reducing LVLM's hallucination in practical applications. The code will be available at https://github.com/purepasser-by/RFI.

RFI: Rectified Flow Intervention for Mitigating Object Hallucination in Large Vision-Language Models

Data poisoning is a training-time attack that undermines the trustworthiness of learned models. In a targeted data poisoning attack, an adversary manipulates the training dataset to alter the classification of a targeted test point. Given the typically large size of training dataset, manual detection of poisoning is difficult. An alternative is to automatically measure a dataset's robustness against such an attack, which is the focus of this paper. We consider a threat model wherein an adversary can only perturb the labels of the training dataset, with knowledge limited to the hypothesis space of the victim's model. In this setting, we prove that finding the robustness is an NP-Complete problem, even when hypotheses are linear classifiers. To overcome this, we present a technique that finds lower and upper bounds of robustness. Our implementation of the technique computes these bounds efficiently in practice for many publicly available datasets. We experimentally demonstrate the effectiveness of our approach. Specifically, a poisoning exceeding the identified robustness bounds significantly impacts test point classification. We are also able to compute these bounds in many more cases where state-of-the-art techniques fail.

On Robustness of Linear Classifiers to Targeted Data Poisoning

While large language model (LLM)-based user profiling of- fers significant potential for personalization, most existing approaches rely on empirical heuristics and lack grounding in the psychological mechanism that drive human behavior. In this paper, we introduce TRIPLE (Theory-guided Rea- soning for Intent and habIt Profiling with LLMs for pEr- sonalization), a novel framework that systematically inte- grates dual-process theory from social psychology into LLM- based user modeling. TRIPLE (1) constructs a habitual be- havior profile by identifying repeated patterns over time to model automatic responses; (2) builds an intentional behav- ior profile by inferring user attitudes, subjective norms and perceived behavioral control based on the Theory of Planned Behavior (TPB); and (3) generates behavioral rationale that reveal the interaction between habitual and intentional pro- cesses to predict user behavior in context-specific situations. We evaluate TRIPLE on five personalization tasks from the LaMP benchmark using multiple open-source LLMs. Re- sults show that TRIPLE consistently outperforms existing in- context learning methods, with especially pronounced gains on complex generative tasks such as headline and title gen- eration.Qualitative analyses further demonstrate that the pro- files and reasoning paths generated by TRIPLE provide inter- pretable and psychologically grounded explanations of user behavior. These findings provide strong evidence that incor- porating validated behavioral theories into LLM-based per- sonalization enhances both predictive performance and inter- pretability, paving a way for theory-driven, socio-cognitively informed user modeling.

TRIPLE: Theory-Driven Integration of Planned and Habitual Behaviors for LLM-based Personalization

Communication is essential in coordinating the behaviors of multiple agents. However, existing methods primarily emphasize content, timing, and partners for information sharing, often neglecting the critical aspect of integrating shared information. This gap can significantly impact agents' ability to understand and respond to complex, uncertain interactions, thus affecting overall communication efficiency. To address this issue, we introduce M2I2, a novel framework designed to enhance the agents' capabilities to assimilate and utilize received information effectively. M2I2 equips agents with advanced capabilities for masked state modeling and joint-action prediction, enriching their perception of environmental uncertainties and facilitating the anticipation of teammates' intentions. This approach ensures that agents are furnished with both comprehensive and relevant information, bolstering more informed and synergistic behaviors. Moreover, we propose a Dimensional Rational Network, innovatively trained via a meta-learning paradigm, to identify the importance of dimensional pieces of information, evaluating their contributions to decision-making and auxiliary tasks. Then, we implement an importance-based heuristic for selective information masking and sharing. This strategy optimizes the efficiency of masked state modeling and the rationale behind information sharing. We evaluate M2I2 across diverse multi-agent tasks, the results demonstrate its superior performance, efficiency, and generalization capabilities, over existing state-of-the-art methods in various complex scenarios.

M2I2: Learning Efficient Multi-Agent Communication via Masked State Modeling and Intention Inference

Frontier AI developers are relying on layers of safeguards to protect against catastrophic misuse of AI systems. Anthropic guards their latest Claude 4 Opus model using one such defense pipeline, and other frontier developers including Google DeepMind and OpenAI pledge to soon deploy similar defenses. However, the security of such pipelines is unclear, with limited prior work evaluating or attacking these pipelines. We address this gap by developing and red-teaming an open-source defense pipeline. 1 First, we find that a novel few-shot-prompted input and output classifier outperforms state-of-the-art open-weight safeguard model ShieldGemma across three attacks and two datasets, reducing the attack success rate (ASR) to 0% on the catastrophic misuse dataset ClearHarm. Second, we introduce a STaged AttaCK (STACK) procedure that achieves 71% ASR on ClearHarm in a black-box attack against the few-shot-prompted classifier pipeline. Finally, we also evaluate STACK in a transfer setting, achieving 33% ASR, providing initial evidence that it is feasible to design attacks with no access to the target pipeline. We conclude by suggesting specific mitigations that developers could use to thwart staged attacks.

STACK: Adversarial Attacks on LLM Safeguard Pipelines

Many organizations are increasingly relying on unstructured documents such as PDFs and scanned forms to sup-port downstream large language model (LLM) services, including search, summarization, and recommendation. However, traditional OCR systems struggle with diverse layouts of documents, leading to frequent errors and high costs of labor. So, this study developed DATALUX - a robust document layout system that transforms unstructured documents into structured, machine-readable data suitable for automation. Built on a transformer-based detector, DATA-LUX incorporates several modules for layout refinement, text-visual fusion, and layer-wise optimization to improve coherence and generalization across diverse layouts. Around January 2025, we successfully deployed DATA-LUX into one of the largest academic content service firms (Nurimedia) in South Korea. This firm faced the challenge of extracting metadata and references from thousands of academic papers submitted in various formats. Also, the existing LLM-based tools provided unreliable results. So, they needed to process them manually, creating bottlenecks in both labor and time. However, DATALUX enabled the automatic structuring of over 100,000 research papers a year, improving extraction accuracy to over 97%, reducing costs by more than USD 185K annually, and accelerating processing speed by 8.7 times. These deployment results suggest that DATALUX enables scalable and efficient document automation in complex and high-volume environments successfully. We thus believe that our DATALUX has a significant impact on both academia and industry practices.

Downloads

Next from AAAI 2026

Modality-Balanced Collaborative Distillation for Multi-Modal Domain Generalization

Similar lecture

ALERT: An LLM-powered Benchmark for Automatic Evaluation of Recommendation Explanations