Singapore

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate harmful outputs that pose risks to users. 
This challenge underscores the need for robust safeguards that operate across both model inputs and outputs. In this work, we introduce RoGuard 1.0, a state-of-the-art instruction fine-tuned LLM designed to enhance the safety of LLM systems through comprehensive input‚Äìoutput moderation, using a pipeline of LLMs to enhance moderation capability. 
Built on the Llama-3.1-8B-Instruct backbone, our model is instruction fine-tuned to generalize across previously unseen safety taxonomies and demonstrates strong performance on out-of-domain safety benchmarks. 
The instruction fine-tuning process uses a mix of synthetic and open-source safety datasets, augmented with chain-of-thought (CoT) rationales and input inversion to enhance contextual understanding and decision making. 
To support systematic evaluation, we also release RoGuard Evaluation, a new benchmark featuring an extensible safety taxonomy to assess the effectiveness of LLM guardrails and moderation frameworks.

AAAI 2026

Taxonomy-Adaptive Moderation Model with Robust Guardrails for Large Language Models

llm guardrails

safety

fine-tuning

### 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

workshop 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.

Large foundation models (LFMs) transform healthcare AI in prevention, diagnostics, and treatment. However, whether LFMs can provide truly personalized treatment recommendations remains an open question. Recent research has revealed multiple challenges for personalization, including the fundamental generalizability paradox: models achieving high accuracy in one clinical study perform at chance level in others, demonstrating that personalization and external validity exist in tension. This exemplifies broader contradictions in AI-driven healthcare: the privacy-performance paradox, scale-specificity paradox, and the automation-empathy paradox. As another challenge, the degree of causal understanding required for personalized recommendations, as opposed to mere predictive capacities of LFMs, remains an open question. N-of-1 trials -- crossover self-experiments and the gold standard for individual causal inference in personalized medicine -- resolve these tensions by providing within-person causal evidence while preserving privacy through local experimentation. Despite their impressive capabilities, this paper argues that LFMs cannot replace N-of-1 trials. We argue that LFMs and N-of-1 trials are complementary: LFMs excel at rapid hypothesis generation from population patterns using multimodal data, while N-of-1 trials excel at causal validation for a given individual. We propose a hybrid framework that combines the strengths of both to enable personalization and navigate the identified paradoxes: LFMs generate ranked intervention candidates with uncertainty estimates, which trigger subsequent N-of-1 trials. Clarifying the boundary between prediction and causation and explicitly addressing the paradoxical tensions are essential for responsible AI integration in personalized medicine.

Personalization of Large Foundation Models for Health Interventions

Real-world deployment of large vision‚Äìlanguage models (LVLMs) makes everyday photos vulnerable to unintended geolocation inference, motivating techniques that enable safe, user-controllable personalization and privacy-aware deployment. We present Adversarial Tiled Location Anonymity Shield (ATLAS), a fully user-side, zero-query, black-box image-layer adaptation module that can be inserted before any LVLM to control the visibility of geospatial and contextual cues under strict perceptual constraints. ATLAS learns such modulations through a Mixture-of-Tiles (MoT) formulation: a semantic segmenter decomposes an image into regions, and a compact tile bank is routed by learned semantic gates and assembled per region before blending with the input to yield a perceptually faithful image that misdirects LVLM geolocation inference. ATLAS is trained on multiple frozen surrogate vision encoders (e.g., LLaMA-4 vision tower, CLIP, BLIP), each paired with lightweight GeoHeads for geolocation supervision; tower-wise losses are aggregated to guide the MoT generator while keeping all backbones frozen. We further explore two complementary training domains: a pixel-space variant perturbing texture and color statistics, and a frequency-space variant modulating low-frequency phase structure to probe distribution-level fragility. On OpenStreetView-5M, ATLAS reduces country-level accuracy by over 40\% and increases mean localization error by over 3,000 km under matched perceptual fidelity. In practice, ATLAS serves as a deployable personalization-safety layer, complementing dialogue-level policies with portable, image-level control, offering a practical path toward privacy-preserving and user-controllable personalization in real-world LVLM deployments.

ATLAS: User-Side Personalization and Privacy Protection Against Geolocation Risks in Large Vision–Language Models

Recent advancements in large language models (LLMs) have significantly enhanced many aspects of research and daily lives. While LLMs are inherently powerful, their performance can be further improved through post-training tailored to specific user needs. For individual users who are unable to directly finetune base models due to resource constraints, classifier guidance offers a more cost-effective solution for controlled text generation. However, traditional ways of applying classifier guidance (CFG) dose not transfer well to Diffusion Large Language Models (DLLMs), which would suffer from instability, criterion mismatch and slow inference. In this work, we propose an efficient approach to utilize and adapt classifier guidance on DLLMs, substantially reducing training and inference time while delivering notable improvements in task performance.

Controlled Text Generation of DLLMs with Efficient Classifier Guidance

Foundation models for knowledge graphs (KGs) achieve strong cohort-level performance in link prediction, yet fail to capture individual user preferences; a key disconnect between general relational reasoning and personalized ranking. We propose GatedBias, a lightweight inference-time personalization framework that adapts frozen KG embeddings to individual user contexts without retraining or compromising global accuracy. Our approach introduces structure-gated adaptation: profile-specific features combine with graph-derived binary gates to produce interpretable, per-entity biases, requiring only ${\sim}300$ trainable parameters. We evaluate GatedBias on two benchmark datasets (Amazon-Book and Last-FM), demonstrating statistically significant improvements in alignment metrics while preserving cohort performance. Counterfactual perturbation experiments validate causal responsiveness; entities benefiting from specific preference signals show 6--30$\times$ greater rank improvements when those signals are boosted. These results show that personalized adaptation of foundation models can be both parameter-efficient and causally verifiable, bridging general knowledge representations with individual user needs.

Lightweight Inference-Time Personalization for Frozen Knowledge Graph Embeddings

Online grocery shopping presents unique challenges for sequential recommendations due to repetitive purchase patterns and complex item relationships within the baskets. Unlike traditional e-commerce, grocery recommendations must capture both complementary item associations and temporal dependencies across shopping sessions. To address these challenges in Amazon's online grocery business, we propose T-REX, a novel transformer architecture that generates personalized category-level suggestions by learning both short-term basket dependencies and long-term user preferences. Our approach introduces three key innovations: (1) an efficient sampling strategy utilizing dynamic sequence splitting for sparse shopping patterns, (2) an adaptive positional encoding scheme for temporal patterns, and (3) a category-level modeling approach that reduces dimensionality while maintaining recommendation quality. Although masked language modeling techniques like BERT4Rec excel at capturing item relations, they prove less suitable for next basket generation due to information leakage issues. In contrast, T-REX's causal masking approach better aligns with the sequential nature of basket generation, enabling more accurate next-basket predictions. Experiments on large-scale grocery offline data and online A/B tests show significant improvement over existing systems.

T-REX: Transformer-based Category Sequence Generation for Grocery Basket Recommendation

Language identification is a crucial first step in multilingual systems such as chatbots and virtual assistants, enabling linguistically and culturally accurate user experiences. Errors at this stage can cascade into downstream failures, setting a high bar for accuracy. Yet, existing language identification tools struggle with key cases--such as music requests where the song title and user language differ. Open-source tools like LangDetect, FastText are fast but less accurate, while large language models, though effective, are often too costly for low-latency or low-resource settings. We introduce PolyLingua, a lightweight Transformer-based model for in-domain language detection and fine-grained language classification. It employs a two-level contrastive learning framework combining instance-level separation and class-level alignment with adaptive margins, yielding compact and well-separated embeddings even for closely related languages. Evaluated on two challenging datasets‚ÄîAmazon Massive (multilingual digital assistant utterances) and a Song dataset (music requests with frequent code-switching)‚ÄîPolyLingua achieves $99.25\%$ F1 and $98.15\%$ F1, respectively, surpassing Sonnet 3.5 while using 10√ó fewer parameters, making it ideal for compute- and latency-constrained environments.

PolyLingua: Margin-based Inter-class Transformer for Robust Cross-domain Language Detection

We revisit continual pre-training for large language models and argue that progress now depends more on scaling the right structure than on scaling parameters alone. We introduce SCALE, a width-upscaling architecture that inserts lightweight expansion into linear modules while freezing all pre-trained parameters. This preserves the residual and attention topologies and increases capacity without perturbing the base model‚Äôs original functionality. SCALE is guided by two principles: Persistent Preservation, which maintains the base model‚Äôs behavior via preservation-oriented initialization and freezing of the pre-trained weights, and Collaborative Adaptation, which selectively trains a subset of expansion components to acquire new knowledge with minimal interference. We instantiate these ideas as SCALE-Preserve (preservation-first), SCALE-Adapt (adaptation-first), and SCALE-Route, an optional routing extension that performs token-level routing between preservation and adaptation heads. On a controlled synthetic biography benchmark, SCALE mitigates the severe forgetting observed with depth expansion while still acquiring new knowledge. In continual pre-training on a Korean corpus, SCALE variants achieve less forgetting on English evaluations and competitive gains on Korean benchmarks, with these variants offering the best overall stability‚Äìplasticity trade-off. Accompanying analysis clarifies when preservation provably holds and why the interplay between preservation and adaptation stabilizes optimization compared to standard continual learning setups.

SCALE: Upscaled Continual Learning of Large Language Models

This paper explores the advancements in making large language models (LLMs) more human-like. We focus on techniques that enhance natural language understanding, conversational coherence, and emotional intelligence in AI systems. The study evaluates various approaches, including fine-tuning with diverse datasets, incorporating psychological principles, and designing models that better mimic human reasoning patterns. Our findings demonstrate that these enhancements not only improve user interactions but also open new possibilities for AI applications across different domains. Future work will address the ethical implications and potential biases introduced by these human-like attributes.

Enhancing Human-Like Responses in Large Language Models

Large language models (LLMs) are typically aligned to general human preferences via Reinforcement Learning from Human Feedback (RLHF), but aligning them to the values of individual users remains challenging. Existing personalization methods often rely on large reward models or expensive reinforcement learning, limiting use on edge or low-compute settings.
We study Tiny Personal Critic, a lightweight scoring model that personalizes LLM outputs while reducing inference compute via a simple gating policy. The critic embeds (prompt, answer) pairs, predicts scores along 6 interpretable axes (e.g., style, safety, factuality), and aggregates them with a user-specific weight vector $\lambda$ learned from a handful of A/B clicks. At inference, we first sample $k_0$ candidate drafts and expand to $k_1$ only if the critic's top-two margin is below a threshold $\tau$, cutting unnecessary generations when the critic is confident.
Trained on a mix of UltraFeedback, Big5Chat and Arena pairs, with knowledge distillation from factuality and safety teachers, the critic achieves 73\% Arena A/B accuracy initially with uniform $\lambda$, outperforming a no-critic length heuristic(62\%), and an UltraFeedback (60\%). Data from few-clicks shifts selections toward the individual which improves the personalization. We observe ~16.7\% fewer generated tokens on our demo; indicating that total inference compute can go down, not up. In addition, as k grows we observe monotone increses in information gain (log-det of a click-induced Fisher Gram matrix) and in the number of preference axes with sufficient evidence, indicating progressively stronger, broader personalization at fixed compute.
We conducted extensive scaling study which showed that the best accuracy was achieved on mid-size critics while very large critics add floating-point operations per second (FLOPs) without consistent gains. Hence, the critics runtime cost per candidate is relatively negligible during inference. Code will be made publically available.

Tiny Personal Critic: A Lightweight Critic for Low-Compute Personalization

Over the last couple of years, AI Agents have gained significant traction due to substantial progress in the capabilities of underlying General Purpose AI (GPAI) models, enhanced scaffolding techniques, and the promise to drive societal transformation. Companies, researchers, and policy makers have started to consider the different effects that AI agents may have across different dimensions of our lives. However, the literature exploring the broader effects of human-agent interactions is still underdeveloped. In this paper, we review the problem of traffic modulation by autonomous vehicles (AVs) in mixed traffic flows and extrapolate the learnings to the different modes of interaction between humans and AVs to the pair humans-AI agents. In doing so, we propose a preliminary taxonomy of relational archetypes based on literature on Human-Computer Interaction (HCI) and AV-human interaction, and tentatively explore how the resulting framework may lead to new questions regarding human-agent interactions. Our effort is aimed at strengthening existing bridges between these two research communities, which share similar traits: autonomy, fast adoption, high impact, and great potential for economic transformation. Building on previous analogies between AI Agents and AVs (e.g., regarding autonomy levels), we anticipate this paper to spark scholarly debate on the different types of impact that agents may have on our societies, while inviting other researchers to expand the scope of their comparative analysis regarding AI Agents.

Downloads

Next from AAAI 2026

Personalization of Large Foundation Models for Health Interventions

Similar lecture

AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails

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

Personalization of Large Foundation Models for Health Interventions

Similar lecture

AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads