Austria

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.


ACL 2025

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

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

ACL-IJCNLP 2021

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

workshop paper

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*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.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

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 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)

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.

Extended Abstract: Probing-Guided Parameter-Efficient Fine-Tuning for Balancing Linguistic Adaptation and Safety in LLM-based Social Influence Systems

Predicting outcomes in multi-turn dialogues is challenging due to the implicit nature of decision-making and the evolving dynamics between participants. In this work, we explore whether LLM-generated intentions and summaries can facilitate outcome prediction in task-oriented dialogues. These intentions and summaries are designed to capture information at both the utterance (local) and the dialogue (global) level respectively. We evaluate both open-sourced and proprietary LLMs in an in-context-learning setup, to predict the final sale price of an ensuing negotiation at different stages of the conversation. Preliminary results suggest that models augmented with these local and global information can better capture negotiation strategies and concession patterns, thereby improving outcome prediction.



Downloads

Next from ACL 2025

Evaluating Large Language Models for Confidence-based Check Set Selection

Similar lecture

Towards Emotional Support Dialog Systems

.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 ACL 2025

Evaluating Large Language Models for Confidence-based Check Set Selection

Similar lecture

Towards Emotional Support Dialog Systems

Downloads