Morocco

Large Language Models (LLMs) are increasingly embedded in the daily lives of individuals across diverse social classes. This widespread integration raises urgent concerns about the subtle, implicit biases these models may contain. In this work, we investigate such biases through the lens of ethical reasoning, analyzing model responses to scenarios in a new dataset we propose comprising 1,016 scenarios, systematically categorized into ethical, unethical, and neutral types. Our study focuses on dimensions that are socially influential but less explored, including (i) residency status, (ii) political ideology, (iii) Fitness Status, (iv) educational attainment, and (v) attitudes toward AI. To assess LLMs’ behavior, we propose a baseline and employ one statistical test and one metric: a permutation test that reveals the presence of bias by comparing the probability distributions of ethical/unethical scenarios with the probability distribution of neutral scenarios on each demographic group, and a tendency measurement that captures the magnitude of bias with respect to the relative difference between probability distribution of ethical and unethical scenarios. Our evaluations of 12 prominent LLMs reveal persistent and nuanced biases across all five attributes, and Llama models exhibited the most pronounced biases. These findings highlight the need for refined ethical benchmarks and bias-mitigation tools in LLMs.

EACL 2026

Detecting Subtle Biases: An Ethical Lens on Underexplored Areas in AI Language Models Biases

llms

implicit bias

dataset curation

bias and fairness

evaluation

### Welcome to CogSci Conference 2025!

The 47th Annual Meeting of the Cognitive Science Society was a hybrid meeting held in San Francisco. 

<div style="position:relative;padding-top:0;width:900px;height:500px;"><iframe style="position:absolute;border:none;width:100%;height:100%;left:0;top:0;" src="https://online.fliphtml5.com/ebtyf/amvr/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe></div>

#### About

The Cognitive Science Society brings together researchers from around the world who hold a common goal: understanding the nature of the human mind. The mission of the Society is to promote Cognitive Science as a discipline, and to foster scientific interchange among researchers in various areas of study, including Artificial Intelligence, Linguistics, Anthropology, Psychology, Neuroscience, Philosophy, and Education.

The Society is a non-profit professional organization and its activities include sponsoring an annual conference and publishing the journals Cognitive Science and TopiCS.

#### Our History 

* **Society Creation**<br>
The Society was incorporated as a 501(c)(3) non-profit professional organization in Massachusetts in 1979. The organizing committee included Roger Schank, Allan Collins, Donald Norman, and a number of other scholars from psychology, linguistics, computer science, and philosophy. 
<br><br>
* **Conference Creation**<br>
The first conference on cognitive science was held at La Jolla, California in August, 1979, and has occurred annually since then. The proceedings of each conference are published, and those from most years are available through Lawrence Erlbaum Associates, Inc. The annual proceedings of the Cognitive Science Conference represent a major source of information on new work and new ideas in the scientific study of thinking. In 1990, the Society, with help from an anonymous donor, established the David Marr Prize for the best student paper at each annual meeting.
<br><br>
* **Journal Creation**<br>
The Journal, Cognitive Science, began publication in 1976, and is now published by Wiley-Blackwell. The Executive Editor is currently Richard P. Cooper of Birkbeck, University of London, and there are 18 Associate Editors and a 30-member editorial board. It serves as the premier outlet for research reports that intersect two or more disciplines. Copyrights for articles published in the journal are held by the Society. The Governing Board of the Cognitive Science Society voted in late 2006 to found a new journal, Topics in Cognitive Science (topiCS). The Editor in Chief is Wayne Gray, Cognitive Science Department, Rensselaer Polytechnic Institute. The journal seeks to fill a niche not occupied by Cognitive Science Journal or other cognitive science journals. Membership in the Society includes a subscription to Cognitive Science and TopiCS. Copyrights for articles published in the journal are held by the Society.
<br><br>

#### Code of Conduct

By attending the CogSci 2025 Conference, you are required to adhere to the society’s **[Code of Conduct](https://drive.google.com/file/d/1ChPuihLy6jE_BWqfO7J2KKgX35JW2zsM/view?usp=sharing)**.
<br><br>


You need to log in with the email address you registered with. 

Login credentials were sent to you from Underline -  subject line "Welcome to the CogSci 2025 Conference". Please be sure to check your spam/promotional inbox  if you do not see an email confirmation right away.





Please log in to join this event.

To access the site, please register [**here**](https://cognitivesciencesociety.org/registration/).

If you are registered and feel like you are seeing this message by mistake, please make sure you are logged in with the same email that you registered with. 

Please register!

CogSci 2025

The 47th Annual Meeting of the Cognitive Science Society presents the latest research across cognitive science and highlights the theme of Cognition in Context.

technical paper

#### *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

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. 

Grouping, e.g., grouping channels, which is widely used in current integer-based quantization, has become essential for the emerging MXFP4 format. Ideally, each group should contain channels with similar quantization scales. To guide such groups, existing work clusters the channels using scalar proxy, ignoring the token dimension, which we find suboptimal. In this paper, we propose TAGQuant, a simple yet powerful enhancement for such ``group-wise'' quantization. By strategically shuffling channels to group those with similar token-wise activation distributions, TAGQuant ensures better clustering of large- and small-range values. This shuffle operation is hardware-efficient, and seamlessly integrated into the quantization process with only 0.01x latency overhead. TAGQuant reduces relative GSM8K error in both INT4 and MXFP4 formats, by up to 86\% in Llama-3.1-8B-Instruct compared to baselines, validating the effectiveness of our channel shuffling approach for group-wise quantization. Code is publicly available.

TAGQuant: Token-Aware Clustering for Group-Wise Quantization

Curriculum learningвЂ”organizing training data from easy to hardвЂ”has improved efficiency across machine learning domains, yet remains underexplored for language model pretraining. We present the first systematic investigation of curriculum learning in LLM pretraining, training over 200 models across three strategies: vanilla curriculum learning, pacing-based sampling, and interleaved curricula. Using six difficulty metrics spanning linguistic and information-theoretic properties, we evaluate performance on eight benchmarks under three realistic scenarios: limited data, unlimited data, and continual training. Our experiments show that curriculum learning consistently accelerates convergence in early and mid-training phases, reducing training steps by 18-45% to reach baseline performance. When applied as a warmup strategy before standard random sampling, curriculum learning yields sustained improvements up to 3.5%. We identify compression ratio, lexical diversity (MTLD), and readability (Flesch Reading Ease) as the most effective difficulty signals. Our findings demonstrate that data orderingвЂ”orthogonal to existing data selection methodsвЂ”provides a practical mechanism for more efficient LLM pretraining.

Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning

Recently, the use of pretrained language models (PLMs) as soft knowledge bases has gained growing interest, sparking the development of knowledge probes to evaluate their factual knowledge retrieval capabilities. However, existing knowledge probes for generative PLMs that support multi-token entities exhibit quadratic time complexity O(n2), where n corresponds to the number of candidate entities, limiting the size of knowledge graphs used for probing. To address this, we propose DEcoder Embedding-based Relational (DEER) probe, utilizing embedding vectors extracted from generative PLMs. DEER probe achieves effective time complexity of linear order O(n), supports rank-based evaluation metrics including Hit@ k, handles multi-token entity names and enables probing whilst disambiguating homographic tail-entity names. We empirically show that DEER-probe correlates with existing knowledge probes, validating its probing capability, and we demonstrate the practical benefits of its improved scalability.

Cosine Similarity as Logits?: A Scalable Knowledge Probe Using Embedding Vectors from Generative Language Models

Knowledge graphs (KGs) provide structured, verifiable grounding for large language models (LLMs), but current LLM-based systems commonly use KGs as auxiliary structures for text retrieval, leaving their intrinsic quality underexplored. In this work, we propose Wikontic, a multi-stage pipeline that constructs KGs from open-domain texts by extracting candidate triplets with qualifiers, enforcing Wikidata-based type and relation constraints, and normalizing entities to reduce duplication. The resulting KGs are compact, ontology-consistent, and well-connected; on MuSiQue, the correct answer entity appears in 96% of generated triplets. On HotpotQA, our triplets-only setup achieves 76.0 F1, and on MuSiQue 59.8 F1, matching or surpassing several retrieval-augmented generation baselines that still require textual context. In addition, Wikontic attains state-of-the-art information-retention performance on the MINE-1 benchmark (86%), outperforming prior KG construction methods. Wikontic is also efficient at build time: KG construction uses less than 1,000 output tokens, about 3 x fewer than AriGraph and < 1/20 of GraphRAG. The proposed pipeline improves the quality of the generated KG and offers a scalable solution for leveraging structured knowledge in LLMs. Wikontic is available at https://github.com/screemix/Wikontic.

Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models

Argument mining (AM) involves extracting argument components and predicting relations between them to create argumentative graphs, which are essential for applications requiring argumentative comprehension. To automatically provide high-quality graphs, previous works require a large amount of human-annotated training samples to train AM models. Instead, we leverage a large language model (LLM) to assign pseudo-labels to training samples for reducing reliance on human-annotated training data. However, the training data weakly-labeled by the LLM are too noisy to develop an AM model with reliable performance. In this paper, to improve the model performance, we propose a center-based component detector that refines the boundaries of the detected components and a relation denoiser to deal with noise present in the pseudo-labels when classifying relations between detected components. Experimentally, our AM model improves the boundary detection obtained from the LLM by up to16 % in terms of IoU75 and of the relation classification obtained from the LLM by up to 12% in terms of macro-F1 score. Our AM model achieves new state-of-the-art performance in weakly-supervised AM, showing up to a 6% improvement over the state-of-the-art component detector and up to a 7% improvement over the state-of-the-art relation classifier. Additionally, our model uses less than 20% of human-annotated data to match the performance of state-of-the-art fully-supervised AM models.

Weakly-supervised Argument Mining with Boundary Refinement and Relation Denoising

Small language models (sLLMs) are increasingly deployed on-device, where imperfect user prompts--typos, unclear intent, or missing context--can trigger factual errors and hallucinations. Existing automatic prompt optimization (APO) methods were designed for large cloud LLMs and rely on search that often produces long, structured instructions; when executed under an on-device constraint where the same small model must act as optimizer and solver, these pipelines can waste context and even hurt accuracy. We propose POaaS, a minimal-edit prompt optimization layer that routes each query to lightweight specialists (Cleaner, Paraphraser, Fact-Adder) and merges their outputs under strict drift and length constraints, with a conservative skip policy for well-formed prompts. Under a strict fixed-model setting with Llama-3.2-3B and Llama-3.1-8B, POaaS improves both task accuracy and factuality while representative APO baselines degrade them, and POaaS recovers up to +7.4% under token deletion and mixup. Overall, per-query conservative optimization is a practical alternative to search-heavy APO for on-device sLLMs.

POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs

Knowledge graphs like DBpedia enable structured fact verification, but the relative contributions of symbolic structure, neural semantics, and evidence grounding remain unclear. We present a systematic study on FACTKG (108,675 claims) comparing symbolic, neural, and LLM-based approaches. Our symbolic baseline using 29 hand-crafted features covering graph structure, entity coverage, and semantic relation type achieves 66.54% accuracy, while BERT over linearized subgraphs reaches 92.68% and graph neural networks plateau at 70%, demonstrating that token-level semantics outperform both symbolic features and message passing. Using GPT-4.1-mini to filter training data, budget-matched controls show that token-budget control recovers most of the gap over truncation-dominated inputs, while LLM semantic selection adds +1.31 points beyond lexical heuristics (78.85% filtered vs. 77.54% heuristic vs. 52.70% unfiltered), showing that semantic relevance, not just evidence quantity, governs learnability. Finally, comparing 300 test claims under memorization (claim-only) versus KG-grounded reasoning with chain-of-thought, we find KG grounding improves GPT-4o-mini and GPT-4.1-mini accuracy by 12.67 and 9.33 points respectively, with models citing specific triples for interpretability. These results demonstrate that neural semantic representations and explicit KG evidence grounding are highly effective for robust, interpretable fact verification.



Evidence Grounding vs. Memorization: Why Neural Semantics Matter for Knowledge Graph Fact Verification

utomated fact verification systems typically assume static truth values, overlooking that many real-world claims are time-dependent. We introduce Temporal Fact Verification (TFV), a framework that explicitly models temporal dynamics through timestamp aware evidence retrieval and temporal entailment reasoning. Our contributions include: (1) TempFact, a dataset of 15,423 claims annotated with temporal validity intervals across static, dynamic, and underspecified categories; (2) a novel pipeline integrating temporal signal extraction, learned temporal embeddings, and joint semantic-temporal reasoning; and (3) comprehensive experiments showing TFV achieves 78.3% accuracy on dynamic claims, significantly outperforming state-of-the-art baselines (p < 0.001). Our work establishes temporal reasoning as essential for fact verification in evolving information environments.

Temporal Fact Verification: Timestamp-Aware Evidence Retrieval and Temporal Entailment for Time-Evolving Claims

Today, search is used by LLMs to support retrieval-augmented generation as well as by humans. In this new setting, how does what we want from a search engine change, and what are promising approaches to take? I will describe work on two themes related to these questions: (1) retrieving documents to support complex information needs in the context of long-form retrieval-augmented generation and (2) exploring learned sparse retrieval as a promising paradigm for first-stage retrieval. In the former line of work, I will discuss search systems aimed at maximizing coverage of relevant information and approaches for evaluating their ability to do so independent of a generation system. In the latter line of work, I will describe research positioning learned sparse retrieval as a compelling alternative to dense retrieval.

Search with Complex Topics and Learned Sparse Retrieval

Language is one of the richest and most complex human cognitive capacities. Yet, we lack a model organism to study its underlying neural mechanisms: unlike other important cognitive capacities, such as vision or memory, language does not have a clear counterpart in non-human animals, leaving a gap in our ability to develop and test mechanistic hypotheses. In recent years, large language models (LLMs) have emerged as the closest computational analogs we have but how can we use them effectively as model organisms for language in the human brain? In this talk, I will discuss the promise and challenges of this approach. I will present our recent work on brain-tuning using naturalistic brain recordings to refine LLMs so that their internal representations and processing better align with human neural data. But beyond representational similarity, a key question remains: do LLMs rely on mechanisms that are similar to those in the brain? And at what level of abstraction should we assess this similarity? This research direction aims to transform LLMs from mere engineering artifacts into powerful scientific tools for uncovering how the brain supports our most distinctive cognitive ability.

Downloads

Next from EACL 2026

TAGQuant: Token-Aware Clustering for Group-Wise Quantization

Similar lecture

Quantifying Risk Propensities of Large Language Models: Ethical Focus and Bias Detection through Role-Play

.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 EACL 2026

TAGQuant: Token-Aware Clustering for Group-Wise Quantization

Similar lecture

Quantifying Risk Propensities of Large Language Models: Ethical Focus and Bias Detection through Role-Play

Downloads