Austria

When a crisis hits, people often turn to social media to ask for help, offer help, find out how others are doing, and decide what they should do. The growth of social media use during crises has been helpful to aid providers as well, giving them a nearly immediate read of the on-the-ground situation that they might not otherwise have. The amount of crisis-related content posted to social media over the past two decades has been explosive, which, in turn, has been a boon to Language Technology (LT) researchers. In this study, we conducted a systematic survey of 355 papers published in the past five years to better understand the expanding growth of LT as it is applied to crisis content, specifically focusing on corpora built over crisis social media data as well as systems and applications that have been developed on this content. We highlight the challenges and possible future directions of research in this space. Our goal is to engender interest in the LT field writ large, in particular in an area of study that can have dramatic impacts on people’s lives. Indeed, the use of LT in crisis response has already been shown to save people’s lives.


ACL 2025

Tapping into Social Media in Crisis: A Survey

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible. The experience for on-site participants would closely approximate a normal pre-COVID *ACL conference, with 5-6 thematically organized parallel sessions and live Q/A and interactive discussion immediately after the talks. Presentations by virtual participants will be equitably interleaved with those of on-site participants, projected on the auditorium screens as if on-site, and also followed immediately by live Q/A and interactive discussion at a time during reasonable waking hours for the virtual presenter. For all participants, on-site and virtual, who are unable to attend a session due to either time-zone issues or because they are participating in another session live, talk recordings and slides will be available online at a minimum after the live presentation (and in many cases before as well), and questions may be submitted in advance on session-specific discussion boards and answered live in session with the usual visual aids if desired.

<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/ceby/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>

Please Note: The EMNLP registration system is not currently connected to the underline site as we are still in the process of building out EMNLP 2021. You will receive access instructions from underline the week of November 1st. 

Access is given only to EMNLP upon registration, if you have not registered please do so [here](https://2021.emnlp.org/registration).

Registered attendees will receive access the week of November 1st.

EMNLP 2021

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible.

workshop paper

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair:<br>
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for  Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025.  ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am  deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.*<br>
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)<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 ACL 2025". 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 need to log in with the **email address you registered with**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Effective emotional support in conversation requires strategic decision making, as it involves complex, context-sensitive reasoning tailored to diverse individual needs. The Emotional Support Conversation framework addresses this by organizing interactions into three distinct phases—exploration, comforting, and action—which guide strategy selection during response generation. While multitask learning has been applied to jointly optimize strategy prediction and response generation, it often suffers from task interference due to conflicting learning objectives. To overcome this, we propose the Strategy-Aware Refinement Module (STAR), which disentangles the decoder’s hidden states for each task and selectively fuses them via a dynamic gating mechanism. This design preserves task-specific representations while allowing controlled information exchange between tasks, thus reducing interference. Experimental results demonstrate that STAR effectively reduces task interference and achieves state-of-the-art performance in both strategy prediction and supportive response generation.


STAR: Strategy-Aware Refinement Module in Multitask Learning for Emotional Support Conversations

Large Language Models (LLMs) have shown promise in automating high-labor data tasks, but the adoption of LLMs in high-stake scenarios faces two key challenges: their tendency to answer despite uncertainty and their difficulty handling long input contexts robustly. We investigate commonly used off-the-shelf LLMs’ ability to identify low-confidence outputs for human review through check set selection–a process where LLMs prioritize information needing human judgment. Using a case study on social media monitoring for disaster risk management, we define the “check set” as a list of tweets escalated to the disaster manager when the LLM has the least confidence, enabling human oversight within budgeted effort. We test two strategies for LLM check set selection: individual confidence elicitation – LLM assesses confidence for each tweet classification individually, requiring more prompts with shorter contexts, and direct set confidence elicitation – LLM evaluates confidence for a list of tweet classifications at once, using less prompts but longer contexts. Our results reveal that set selection via individual probabilities is more reliable but that direct set confidence merits further investigation. Direct set selection challenges include inconsistent outputs, incorrect check set size, and low inter-annotator agreement. Despite these challenges, our approach improves collaborative disaster tweet classification by outperforming random-sample check set selection, demonstrating the potential of human-LLM collaboration.


Evaluating Large Language Models for Confidence-based Check Set Selection

The rise of LLM-driven AI characters raises safety concerns, particularly for vulnerable human users with psychological disorders. To address these risks, we propose EmoAgent, a multi-agent AI framework designed to evaluate and mitigate mental health hazards in humanAI interactions. EmoAgent comprises two components: EmoEval simulates virtual users, including those portraying mentally vulnerable individuals, to assess mental health changes before and after interactions with AI characters. It uses clinically proven psychological and psychiatric assessment tools (PHQ-9, PDI, PANSS) to evaluate mental risks induced by LLM. EmoGuard serves as an intermediary, monitoring users’ mental status, predicting potential harm, and providing corrective feedback to mitigate risks. Experiments conducted in popular character-based chatbots show that emotionally engaging dialogues can lead to psychological deterioration in vulnerable users, with mental state deterioration in more than 34.4% of the simulations. EmoGuard significantly reduces these deterioration rates, underscoring its role in ensuring safer AI-human interactions.


EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety

The development of chatbots requires collecting a large number of human-chatbot dialogues to reflect the breadth of users' sociodemographic backgrounds and conversational goals. However, the resource requirements to conduct the respective user studies can be prohibitively high and often only allow for a narrow analysis of specific dialogue goals and participant demographics. In this paper, we propose LLM Roleplay, the first comprehensive method integrating multi-turn human-chatbot interaction simulation, explicit persona construction from sociodemographic traits, goal-driven dialogue planning, and robust handling of conversational failures, enabling broad utility and reliable dialogue generation. To validate our method, we collect natural human-chatbot dialogues from different sociodemographic groups and conduct a user study to compare these with our generated dialogues. We evaluate the capabilities of state-of-the-art LLMs in maintaining a conversation during their embodiment of a specific persona and find that our method can simulate human-chatbot dialogues with a high indistinguishability rate.

LLM Roleplay: Simulating Human-Chatbot Interaction

This paper presents PROTECT, a novel policy-driven organizational value taxonomy designed to enhance ethical compliance and trust within organizations. Drawing on established human value systems and leveraging large language models, PROTECT generates values tailored to organizational contexts and clusters them into a refined taxonomy. This taxonomy serves as the basis for creating a comprehensive dataset of compliance scenarios, each linked to specific values and paired with both compliant and non-compliant responses. By systematically varying value emphasis, we illustrate how different LLM personas emerge, reflecting diverse compliance behaviors. The dataset, directly grounded in the taxonomy, enables consistent evaluation and training of LLMs on value-sensitive tasks. While PROTECT offers a robust foundation for aligning AI systems with organizational standards, our experiments also reveal current limitations in model accuracy, highlighting the need for further improvements. Together, the taxonomy and dataset represent complementary, foundational contributions toward value-aligned AI in organizational settings.

PROTECT: Policy-Related Organizational Value Taxonomy for Ethical Compliance and Trust

As LLMs are increasingly used in global conversational settings, concerns remain about their ability to handle complex sociocultural contexts. This study evaluates LLMs’ empathetic understanding in Korean—a high-context language—using a pragmatics-based Discourse Completion Task (DCT) focused on interpretive judgment rather than generation. We constructed a dataset varying relational hierarchy, intimacy, and emotional valence, and compared responses from proprietary and open-source LLMs to those of Korean speakers. Most LLMs showed over-empathizing tendencies and struggled with ambiguous relational cues. Neither model size nor Korean fine-tuning significantly improved performance. While humans reflected relational nuance and contextual awareness, LLMs relied on surface strategies. These findings underscore LLMs’ limits in socio-pragmatic reasoning and introduce a scalable, culturally flexible framework for evaluating socially-aware AI.



Too Polite to be Human: Evaluating LLM Empathy in Korean Conversations via a DCT-Based Framework

Masculine discourse words are discourse terms that are both socially normative and statistically associated with male speakers. We propose a twofold framework for (i) the large-scale discovery and analysis of gendered discourse words in spoken content via our Gendered Discourse Correlation Framework; and (ii) the measurement of the gender bias associated with these words in LLMs via our Discourse Word-Embedding Association Test. We focus our study on podcasts, a popular and growing form of social media, analyzing 15,117 podcast episodes. We analyze correlations between gender and discourse words -- discovered via LDA and BERTopic. We then find that gendered discourse-based masculine defaults exist in the domains of business, technology/politics, and video games, indicating that these gendered discourse words are socially influential. Next, we study the representation of these words from a state-of-the-art LLM embedding model from OpenAI, and find that the masculine discourse words have a more stable and robust representation than the feminine discourse words, which may result in better system performance on downstream tasks for men. Hence, men are rewarded for their discourse patterns with better system performance -- and this embedding disparity constitutes a representational harm and a masculine default.

Masculine Defaults via Gendered Discourse in Podcasts and Large Language Models

Courtrooms are places where lives are determined and fates are sealed, yet they are not impervious to manipulation. Strategic use of manipulation in legal jargon can sway the opinions of judges and affect the decisions. Despite the growing advancements in NLP, its application in detecting and analyzing manipulation within the legal domain remains largely unexplored. Our work addresses this gap by introducing LegalCon, a dataset of 1,063 annotated courtroom conversations labeled for manipulation detection, identification of primary manipulators, and classification of manipulative techniques, with a focus on long conversations. Furthermore, we propose CLAIM, a two-stage, Intent-driven Multi-agent framework designed to enhance manipulation analysis by enabling context-aware and informed decision-making. Our results highlight the potential of incorporating agentic frameworks to improve fairness and transparency in judicial processes. We hope that this contributes to the broader application of NLP in legal discourse analysis and the development of robust tools to support fairness in legal decision-making. Our code and data are available at \href{https://github.com/Disha1001/CLAIM}{CLAIM}.

Unmasking the Strategists: An Intent-Driven Multi-Agent Framework for Analyzing Manipulation in Courtroom Dialogues

In this study, we address the challenge of consistently following emotional support strategies in long conversations by large language models (LLMs). We introduce the Strategy-Relevant Attention (SRA) metric, a model-agnostic measure designed to evaluate the effectiveness of LLMs in adhering to strategic prompts in emotional support contexts. By analyzing conversations within the Emotional Support Conversations dataset (ESConv) using LLaMA models, we demonstrate that SRA is significantly correlated with a model's ability to sustain the outlined strategy throughout the interactions. Our findings reveal that the application of SRA-informed prompts leads to enhanced strategic adherence, resulting in conversations that more reliably exhibit the desired emotional support strategies over longer conversations. Furthermore, we contribute a comprehensive, multi-branch synthetic conversation dataset for ESConv, featuring a variety of strategy continuations informed by our optimized prompting method. The code and data are publicly available on our Github.

Steering Conversational Large Language Models for Long Emotional Support Conversations

Designing effective LLMs for social influence (SI) tasks demands controlling linguistic output such that it adapts to context (such as user attributes, history etc.) while upholding ethical guardrails. Standard Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA struggle to manage the trade-off between adaptive linguistic expression and safety and they optimize based on overall objectives without differentiating the functional roles of internal model components. Therefore, we introduce Probing-Guided PEFT (PG-PEFT), a novel fine-tuning strategy which utilizes interpretability probes to identify LLM components associated with context-driven linguistic variations versus those linked to safety violations (e.g., toxicity, bias). This functional map then guides LoRA updates, enabling more targeted control over the model's linguistic output. We evaluate PG-PEFT on SI tasks (persuasion, negotiation) and linguistic adaptability with safety benchmarks against standard PEFT.

Downloads

Next from ACL 2025

STAR: Strategy-Aware Refinement Module in Multitask Learning for Emotional Support Conversations

Similar lecture

Multi-task Learning to Enable Location Mention Identification in the Early Hours of a Crisis Event