Singapore

Large language models (LLMs) frequently demonstrate reasoning limitations, often conflating content plausibility with logical validity. This can result in biased inferences, where plausible arguments are incorrectly deemed logically valid or vice versa. 
This paper investigates how to mitigate content biases on reasoning through activation steering, an inference-time intervention technique that modulates model activations. After localising the layers responsible for formal and material inference through probing, we investigate contrastive activation steering methods using a controlled syllogistic reasoning dataset that covers 24 types of logical argument schemes, designed to disentangle formal validity from content plausibility. An extensive empirical analysis reveals that contrastive steering consistently supports linear control over content biases. However, we observe that a static steering approach is insufficient for achieving improvements on all the tested models. We then leverage the possibility to control content effects by dynamically determining the value of the steering parameters via fine-grained conditional methods. We found that conditional steering is effective in reducing biases on unresponsive models, achieving up to 15% absolute improvement in formal reasoning accuracy with a newly introduced kNN-based conditional method. Finally, we found that steering for content effects is robust to prompt variations, incurs minimal side effects on multilingual language modeling capabilities, and can partially generalize to out-of-distribution tasks. Practically, this paper demonstrates that activation-level interventions can offer a scalable test-time strategy for enhancing the robustness of LLMs, contributing towards more systematic and unbiased reasoning

AAAI 2026

Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering

content biases

activation steering

formal reasoning

large language models

#### *Message from the General Chair, Aline Villavicencio*
I’m delighted and honoured to welcome you to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), taking place in the beautiful city of Rabat, in Morocco, in March 24-29, 2026. EACL is the flagship European conference of the Association and EACL 2026 proudly continues our field’s tradition of excellence in scholarship, innovation, and inclusivity. I am deeply grateful to the many volunteers whose dedication, generosity, and tireless efforts have made this conference possible.
For the first time EACL is being hosted in the African continent. This is an important milestone for our community, and we are grateful to our Moroccan hosts for enabling this historic moment by bringing this edition of EACL to Rabat. We are also delighted that the Second Arabic NLP School is co-located with EACL. We hope attendees enjoy this wonderful opportunity to strengthen ties with the Computational Linguistics communities across the African continent. *[Read full message](https://drive.google.com/file/d/14NlmHvwM6fPJuMmOvVh7K0vtQbEyv3SZ/view?usp=sharing)*<br><br>

<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://underline.io/events/522/reception','_blank')">Go to Workshops and Tutorials Program</button></html>
<br><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 EACL 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://2026.eacl.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/eacl2026

Registration Required

EACL 2026

Welcome to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL). EACL 2026 will be held in Rabat, Morocco, from March 24–29, 2026. 

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.<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.

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 

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.

Multi-view clustering (MVC) has recently garnered increasing attention for its ability to partition unlabeled samples into distinct clusters by leveraging complementary and consistent information from different views. Existing MVC methods primarily combine deep neural networks with contrastive learning for cross-view representation learning, yet often overlook the inherent global-local structural relationships among samples. While GNN-based methods capture local structures, they struggle to model global dependencies, leading to inferior inter-cluster separability. In contrast, Transformer-based methods excel at global aggregation but suffer from quadratic complexity, and their attention smoothing effect weakens fine-grained local structures, resulting in suboptimal intra-cluster compactness. To address these limitations, we propose a novel end-to-end MVC framework called Mamba-Driven Multi-View Discriminative Clustering via Global-Local Cross-View Sequence Modeling (MGLC). By flexibly constructing multi-view sequences, MGLC fully exploits the efficient sequence modeling capabilities of Mamba to jointly model cross-view dependencies and global-local structural relationships among samples. Furthermore, MGLC introduces a Cross-Mamba Fusion module to dynamically integrate cross-view and global-local structural representations. Additionally, MGLC incorporates a Dual Calibration Contrastive Learning module, guided by high-confidence pseudo-labels, that adaptively refines both feature and semantic representations while mitigating false negatives among semantically similar samples. Extensive comparative experiments and ablation studies demonstrate the effectiveness of MGLC.

Mamba-Driven Multi-View Discriminative Clustering via Global-Local Cross-View Sequence Modeling

Structure-Based Drug Design (SBDD) has emerged as a popular approach in drug discovery, leveraging three-dimensional protein structures to generate drug ligands. However, existing generative models encounter several key challenges: (1) Incorporating boundary condition constraints, (2) Integrating hierarchical structural conditions and (3) Ensuring spatial modeling fidelity. To overcome these limitations, we propose SculptDrug, a spatial condition-aware generative model based on Bayesian Flow Networks (BFNs). 
First, SculptDrug follows a BFNs-based framework and employs a progressive denoising strategy to ensure spatial modeling fidelity, iteratively refining atom positions while enhancing local interactions for precise spatial alignment.
Second, we introduce the Boundary Awareness Block, which incorporates protein surface constraints into the generative process to ensure that the generated ligands are geometrically compatible with the target protein.
Finally, we design a Hierarchical Encoder that captures global structural context while preserving fine-grained molecular interactions, ensuring overall consistency and accurate ligand–protein conformations.
We evaluate SculptDrug on the CrossDocked dataset, and experimental results demonstrate that SculptDrug outperforms state-of-the-art baselines, proving the efficacy of spatial condition-aware modeling.

SculptDrug: A Spatial Condition-Aware Bayesian Flow Model for Structure-based Drug Design

Space computing devices expand handwritten input from two-dimensional screens into three-dimensional space, providing an unrestricted interactive experience. Due to the high degree of freedom and lack of tactile feedback in in-air handwriting, handwritten characters not only become less legible but also lose the writer's personal style. This paper proposes a method for reconstructing discrete in-air handwriting using continuous diffusion models, capturing the writing process and style from a small number of user-provided handwritten tracks and images, to restore the legibility of characters and mimics the writer's style. We represent handwritten track data in binary form and model it with continuous diffusion models, recovering discrete handwritten track data through threshold processing. Our approach reconstructs in-air handwritten characters in two stages. During the content preservation phase, we propose a partial noise injection strategy based on reference sequence modeling, using the content information of the original character as a guiding condition to maintain content consistency in handwritten character. In the style aggregation phase, we adaptively fuse the visual style of the handwritten in the image modality with the dynamic writing process in the sequence modality, overcoming issues of insufficient style capture due to noise interference in the backward process. Qualitative and quantitative experiments demonstrate the superiority of our method.

Gracefully Air-Written: Enhancing the Legibility and Style Consistency of In-Air Handwriting

Dynamic brain networks provide a powerful representation for capturing temporal variations in functional brain connectivity and have gained increasing attention in brain disease diagnosis. However, most existing methods extract features from isolated time windows, making it difficult to capture the high-order dynamic evolution of brain activity. Moreover, these methods often neglect the functional heterogeneity among brain regions, thereby limiting diagnostic performance. To address these limitations, we propose **HyperDiag**, a novel temporal-regional **Hyper**graph learning via topology-enhanced state propagation for brain disease **Diag**nosis. Specifically, we first design a dual-level hypergraph learning strategy: a temporally-evolving hypergraph message passing strategy to capture dynamic high-order dependencies within and across time windows, and meanwhile, a region-wise functional hypergraph learning strategy to capture regional dependencies. Subsequently, we construct a topology-enhanced selective state-space propagation network to integrate complementary information from both the temporally-evolving and region-wise features. Extensive experiments on four brain disorder datasets (ABIDE-I, ADNI, REST-meta-MDD, and Epilepsy) demonstrate that HyperDiag not only outperforms state-of-the-art methods but also identifies biologically meaningful abnormal connections, offering potential biomarkers for clinical interpretation. Our code is available in the Appendix.

HyperDiag: Temporal–Regional Hypergraph Learning via Topology-Enhanced State Propagation for Brain Disease Diagnosis

The rapid advancement of generative models demands robust detection of synthetic images. Existing foundation model-based methods fall into either perceptual or generative paradigms, each with inherent limitations: perceptual models capture high-level semantics but miss subtle artifacts; generative models highlight fine-grained flaws yet overlook semantic inconsistency. We fundamentally rethink foundation model application in AI-generated image detection by proposing **SynerDetect**, a hierarchical synergistic framework that enables deep cross-paradigm integration, establishing a unified forensic paradigm. SynerDetect introduces Cross-Model Interactive Distillation (CMID) to infuse generative forensic signals into perceptual encoders via prompt-guided reconstruction, while discriminative latent noise features are extracted through model inversion. Further, Optimal Transport-Guided Discriminative Contrastive Learning (OT-DCL) structurally aligns and integrates heterogeneous forensic representations, consolidating them into a robust, unified detection space. SynerDetect sets a new performance paradigm on AIGCDetectBenchmark and GenImage, and attains **5.20\%** accuracy gains on the challenging Chameleon benchmark, whose synthetic images consistently pass the Visual Turing Test. These results demonstrate robust, real-world generalization enabled by our unified cross-paradigm framework.

SynerDetect: Hierarchical Synergistic Learning for Generalizable AI-Generated Image Detection

Large Language Model (LLM) agent systems have advanced rapidly, driven by their strong generalization in zero-shot settings. To further enhance reasoning and accuracy on complex tasks, Multi-Agent Debate (MAD) has emerged as a promising framework that engages multiple LLM agents in structured debates to encourage diverse reasoning. However, triggering MAD for every input instance is inefficient, as it incurs substantial computational (token) cost and may even degrade accuracy by overturning correct single-agent answers. To address these limitations, we propose intelligent Multi-Agent Debate (iMAD), a token-efficient framework that selectively triggers MAD only when it is likely to be beneficial (i.e., correcting an initially wrong answer) in the zero-shot setting. To achieve this goal, iMAD learns generalizable model behaviors to make accurate debate decisions in the zero-shot setting. Specifically, it first prompts a single agent to produce a structured self-critique response, from which we extract over 40 interpretable linguistic and semantic features capturing hesitation cues. A lightweight classifier, based on Multi-Layer Perceptron and trained using our proposed FocusCal loss, then determines whether to trigger MAD, enabling robust zero-shot decisions without dataset-specific tuning. We evaluate iMAD on six (visual) question answering datasets against five competitive baselines. iMAD significantly reduces token usage (by up to 92%) while also improving final answer accuracy (by up to 13.5%).

iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference

Virtual Immunohistochemistry (IHC) staining technology employs generative models to directly synthesize IHC images from Hematoxylin and Eosin (H&E) images, reducing reliance on chemical staining while improving diagnostic efficiency and reducing costs. However, existing virtual staining methods relying on adjacent sections face two critical challenges: insufficient mining of pathological semantics and the spatial misalignment of pathological semantics due to physical discrepancies between sections. To address these, we propose GSGStain, a Graph-Semantic Guided Learning for virtual Staining. Our method innovatively transforms the problem from pixel space to graph space, enabling semantic noise correction for spatial misalignment features. Specifically, to capture the rich pathological semantics, we construct a cell graph from the H\&E image to encode tissue architecture, annotating nodes with noisy biomarker semantic features derived from misaligned adjacent IHC sections. Furthermore, to correct for the semantic misalignment, a Graph Semantic Rectification Module (GSRM) then refines these features using graph contextual reasoning, while a Graph Semantic Consistency Loss ensures alignment between generated IHC images and rectified semantics. Additionally, we propose a dual-branch discriminator to compel the generator to match the empirical distribution of real images, significantly improving generation quality. Extensive experiments on two public benchmarks demonstrate that GSGStain significantly outperforms state-of-the-art methods in both image quality and pathological consistency. This work establishes a new paradigm for semantically robust virtual staining. Our source code is available at https://anonymous.4open.science/r/GSGStain.

Graph-Semantic Guided Learning for Virtual Immunohistochemistry Staining on Consecutive Histology Sections

Audio-visual sound source localization (AV-SSL) estimates the position of sound sources by fusing auditory and visual cues. Current AV-SSL methodologies typically require spatially-paired audio-visual data and cannot selectively localize specific target sources. To address these limitations, we introduce Cross-Instance Audio-Visual Localization (CI-AVL), a novel task that localizes target sound sources using visual prompts from different instances of the same semantic class. CI-AVL enables selective localization without spatially paired data. To solve this task, we propose AV-SSAN, a semantic-spatial alignment framework centered on a Multi-Band Semantic-Spatial Alignment Network (MB-SSA Net). MB-SSA Net decomposes the audio spectrogram into multiple frequency bands, aligns each band with semantic visual prompts, and refines spatial cues to estimate the direction-of-arrival (DoA). To facilitate this research, we construct VGGSound-SSL, a large-scale dataset comprising 13,981 spatial audio clips across 296 categories, each paired with visual prompts. AV-SSAN achieves a mean absolute error of 16.59° and an accuracy of 71.29\%, significantly outperforming existing AV-SSL methods. Code and data will be public upon acceptance.

AV-SSAN: Audio-Visual Selective DOA Estimation Through Explicit Multi-Band Semantic-Spatial Alignment

LLM-based autonomous agents have recently shown strong capabilities in solving complex industrial design tasks. However, in domains aiming for carbon neutrality and high-performance renewable energy systems, current AI-assisted design automation methods face critical challenges in explainability, scalability, and practical usability. To address these limitations, we introduce PHIA (Physics-Informed Autonomous Agent), an LLM-driven system that automates modulation design for power converters in Power Electronics Systems with minimal human intervention. In contrast to traditional pipeline-based methods, PHIA incorporates an LLM-based planning module that interactively acquires and verifies design requirements via a user-friendly chat interface. This planner collaborates with physics-informed simulation and optimization components to autonomously generate and iteratively refine modulation designs. The interactive interface also supports interpretability by providing textual explanations and visual outputs throughout the design process. Experimental results show that PHIA reduces standard mean absolute error by 63.2\% compared to the second-best benchmark and accelerates the overall design process by over 33 times. A user study involving 20 domain experts further confirms PHIA’s superior design efficiency and usability, highlighting its potential to transform industrial design workflows in power electronics.

Physics-Informed Autonomous LLM Agents for Explainable Power Electronics Modulation Design

Traditional video reasoning segmentation methods rely on supervised fine-tuning, which limits generalization to out-of-distribution scenarios and lacks explicit reasoning. To address this, we propose VideoSeg-R1, the first framework to introduce reinforcement learning into video reasoning segmentation. It adopts a decoupled architecture, modeling the task as a combination of referring image segmentation and video mask propagation. The pipeline includes three stages: (1) a hierarchical text-guided frame sampler to localize key segments and reference frames; (2) a reasoning model that generates explicit chain-of-thought prompts; and (3) a segmentation and propagation stage using SAM2 and XMem to produce and spread pixel-level masks. A task difficulty-aware mechanism is introduced during training to adaptively control reasoning length, improving both efficiency and performance. Experiments on multiple benchmarks demonstrate that VideoSeg-R1 outperforms prior methods in complex reasoning, temporal understanding, and object tracking. Code and models will be released upon acceptance.

Content not yet available

Downloads

Next from AAAI 2026

Mamba-Driven Multi-View Discriminative Clustering via Global-Local Cross-View Sequence Modeling

Similar lecture

Can Activation Steering Generalize Across Languages? A Study on Syllogistic Reasoning in Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

.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

Mamba-Driven Multi-View Discriminative Clustering via Global-Local Cross-View Sequence Modeling

Similar lecture

Can Activation Steering Generalize Across Languages? A Study on Syllogistic Reasoning in Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads