United States

Human cognition constrains how we communicate. Our cognitive biases and preferences interact with the processes that drive language emergence and change in non-trivial ways. A powerful method to discern the roles of cognitive biases and processes like language learning and use in shaping linguistic structure is to build agent-based models. Recent advances in computational linguistics and deep learning sparked a renewed interest in such simulations, creating the opportunity to model increasingly realistic phenomena. These models simulate emergent communication, referring to the spontaneous development of a communication system through repeated interactions between individual neural network agents. However, a crucial challenge in this line of work is that such artificial learners still often behave differently from human learners. Directly inspired by human artificial language learning studies, we proposed a novel framework for simulating language learning and change, which allows agents to first learn an artificial language and then use it to communicate, with the aim of studying the emergence of specific linguistic properties. I will show how we used it to simulate the emergence of a well-known language phenomenon: the word-order/case-marking trade-off. I will also share some recent findings where we test for the presence of a well-known human cross-modal mapping preference (the bouba-kiki effect) in vision-and-language models. Cross-modal associations play an essential role in human language understanding, learning, and evolution, but our findings reveal that multimodal language models do not align well with such human preferences. Finally, I will provide a sneak peek at new findings that reveal what a novel artificial language looks like when it has emerged to adapt to preferences of both humans and LLMs in a hybrid language game experiment.

NAACL 2025

The emergence of language universals in neural agents and vision-and-language models

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

invited talk

### 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!

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

Appraisal theories suggest that emotions arise from subjective evaluations of events, referred to as appraisals. The taxonomy of appraisals is quite diverse, and they are usually given ratings on a Likert scale to be annotated in an experiencer-annotator or reader-annotator paradigm. This paper studies GPT-4 as a reader-annotator of 21 specific appraisal ratings in different prompt settings, aiming to evaluate and improve its performance compared to human annotators. We found that GPT-4 is an effective reader-annotator that performs close to or even slightly better than human annotators, and its results can be significantly improved by using a majority voting of five completions. GPT-4 also effectively predicts appraisal ratings and emotion labels using a single prompt, but adding instruction complexity results in poorer performance. We also found that longer event descriptions lead to more accurate annotations for both model and human annotator ratings. This work contributes to the growing usage of LLMs in psychology and the strategies for improving GPT-4 performance in annotating appraisals.

Assessing the Reliability and Validity of GPT-4 in Annotating Emotion Appraisal Ratings

Psychodynamic conflicts are persistent, often unconscious themes that shape a person’s behaviour and experiences. Accurate diagnosis of psychodynamic conflicts is crucial for effective patient treatment and is commonly done via long, manually scored semi-structured interviews. Existing automated solutions for psychiatric diagnosis tend to focus on the recognition of broad disorder categories such as depression, and it is unclear to what extent psychodynamic conflicts which even the patient themselves may not have conscious access to could be automatically recognised from conversation. In this paper, we propose AutoPsyC, the first method for recognising the presence and significance of psychodynamic conflicts from full-length Operationalized Psychodynamic Diagnostics (OPD) interviews using Large Language Models (LLMs). Our approach combines recent advances in parameter-efficient fine-tuning and Retrieval-Augmented Generation (RAG) with a summarisation strategy to effectively process entire 90 minute long conversations. In evaluations on a dataset of 141 diagnostic interviews we show that AutoPsyC consistently outperforms all baselines and ablation conditions on the recognition of four highly relevant psychodynamic conflicts.

AutoPsyC: Automatic Recognition of Psychodynamic Conflicts from Semi-structured Interviews with Large Language Models

The increasing demand for mental health services has highlighted the need for innovative solutions, particularly in the realm of psychological conversational AI, where the availability of sensitive data is scarce. In this work, we explored the development of a system tailored for mental health support with a novel approach to psychological assessment based on explainable emotional profiles in combination with empathetic conversational models, offering a promising tool for augmenting traditional care, particularly where immediate expertise is unavailable. Our work can be divided into two main parts, intrinsecaly connected to each other. First, we present RACLETTE, a conversational system that demonstrates superior emotional accuracy compared to considered benchmarks in both understanding users’ emotional states and generating empathetic responses during conversations, while progressively building an emotional profile of the user through their interactions. Second, we show how the emotional profiles of a user can be used as interpretable markers for mental health assessment. These profiles can be compared with characteristic emotional patterns associated with different mental disorders, providing a novel approach to preliminary screening and support.

The Emotional Spectrum of LLMs: Leveraging Empathy and Emotion-Based Markers for Mental Health Support

Depression is a highly prevalent and disabling condition that incurs substantial personal and societal costs. Current depression diagnosis involves determining the depression severity of a person through self-reported questionnaires or interviews conducted by clinicians. This often leads to delayed treatment and involves substantial human resources. Thus, several works try to automate the process using multimodal data. However, they usually overlook the following: i) The variable contribution of each modality for each question in the questionnaire and ii) Using ordinal classification for the task. This results in sub-optimal fusion and training methods. In this work, we propose a novel Question-wise Modality Fusion (QuestMF) framework trained with a novel Imbalanced Ordinal Log-Loss (ImbOLL) function to tackle these issues. The performance of our framework is comparable to the current state-of-the-art models on the E-DAIC dataset and enhances interpretability by predicting scores for each question. This will help clinicians identify an individual’s symptoms, allowing them to customise their interventions accordingly. We also make the code for the QuestMF framework publicly available.

Enhancing Depression Detection via Question-wise Modality Fusion

Recent work has suggested detection of cognitive distortions as an impactful task for NLP in the clinical space, but the connection between language-detected distortions and validated mental health outcomes has been elusive. In this work, we evaluate the co-occurrence of (a) 10 distortions derived from language-based detectors trained over two common distortion datasets with (b) 12 mental health outcomes contained within two new language-to-mental-health datasets: DS4UD and iHiTOP. We find higher rates of distortions for those with greater mental health condition severity (ranging from r = 0.16 for thought disorders to r = 0.46 for depressed mood), and that the specific distortions of should statements and fortune telling were associated with a depressed mood and being emotionally drained, respectively. This suggested that language-based assessments of cognitive distortion could play a significant role in detection and monitoring of mental health conditions.

Linking Language-based Distortion Detection to Mental Health Outcomes

Transformers has redefined deep learning research and has become the most prominent architecture across domains such as natural language processing, computer vision, and image processing. Attention mechanism, particularly self-attention, is central to the success of this architecture, which allows the model to capture dependencies across the input sequences. However, the fundamental challenge in understanding self-attention is its intrinsic symmetry. The existing works often consider self-attention as a kernel method, leveraging symmetric kernels based on Mercer’s theorem. However, the self-attention matrices used in the transformer architectures are inherently asymmetric, which leads to an inconsistency
between the theoretical formulation and the practical implementation. The primal-attention, a novel attention mechanism based on kernel singular value decomposition explicitly models the asymmetry.
Therefore, reformulating self-attention using primal-dual representation ensures efficient computation and low-rank approximation that enhances performance and generalization.

Understanding Attention in Asymmetric Kernel Point of View

The past and future of grapheme-to-phoneme conversion

Scientific research is inherently slow, complex, and highly specialized, relying on an iterative cycle of hypothesis generation and validation. Can we create an AI-powered biologist to automate these processes at scale? In this talk, I will outline the key ingredients for building such a system. I will first introduce Biomni, a generalist AI agent that integrates large language models with a vast ecosystem of specialized biological tools, software, and databases. By linking AI-driven reasoning with real-world execution, Biomni enables a broad range of biomedical applications. Building on this foundation, I will introduce BioDiscoveryAgent, an AI system for automated hypothesis generation that optimizes experimental design by identifying the most promising perturbations for screening. By leveraging literature-based reasoning, it significantly outperforms traditional Bayesian optimization approaches. Finally, beyond hypothesis generation, rigorous validation is essential. I will present POPPER, an AI-driven sequential falsification framework that automates hypothesis validation with statistical guarantees, ensuring scientific robustness at scale.

AI Agents for Accelerating Scientific Discovery: From Hypothesis Generation to Experimental Design

TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools

There exist approximately 166 billion small molecules, with 970 million deemed druglike. Similarly there is a vast pool of molecule candidates for new materials. This scarcity underscores the urgent need for innovative approaches, calling upon the NLP community to contribute significantly to medicine and material science. However, the challenges are manifold. Existing large language models (LLMs) alone are insufficient due to their tendency to generate erroneous claims confidently. Moreover, traditional knowledge bases do not adequately address the issue. This gap persists because chemistry language diverges significantly from natural language, demanding specialized domain knowledge, joint molecule and language modeling, and critical thinking. Using drug discovery, personalized drug synergy, and material discovery as case studies, I will present our approaches to tackle these challenges and turn an AI agent into a Medicinal Chemist or Material Scientist. I will share preliminary results from animal testing conducted on drug variants, and newly discovered material variants for efficient Organic Photovoltaic Devices proposed by AI algorithms.

Downloads

Next from NAACL 2025

Assessing the Reliability and Validity of GPT-4 in Annotating Emotion Appraisal Ratings

Similar lecture

Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off" | VIDEO

.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 NAACL 2025

Assessing the Reliability and Validity of GPT-4 in Annotating Emotion Appraisal Ratings

Similar lecture

Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off" | VIDEO

Downloads