Austria

Due to the sensitive nature of personally identifiable information (PII), its owners may have the authority to control its inclusion or request its removal from large-language model (LLM) training. 
Beyond this, PII may be added or removed from training datasets due to evolving dataset curation techniques, because they were newly scraped for retraining, or because they were included in a new downstream fine-tuning stage. We find that the amount and ease of PII memorization is a dynamic property of a model that evolves throughout training pipelines and depends on commonly altered design choices. We characterize three such novel phenomena: (1) similar-appearing PII seen later in training can elicit memorization of earlier-seen sequences in what we call assisted memorization, and this is a significant factor (in our settings, up to 1/3); (2) adding PII can increase memorization of other PII; and (3) removing PII can lead to other PII being memorized.

ACL 2025

Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training

memorization

privacy

language models

### 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)

poster

Effective decision-making in Large Language Models (LLMs) is essential for handling intricate tasks. However, existing approaches prioritize performance but often overlook the balance between effectiveness and computational cost. To address this, we first introduce the 3E Criteria to systematically assess the cost-effectiveness of search strategies, revealing that existing methods often trade significant efficiency for marginal performance gains. To improve LLM decision-making while maintaining efficiency, we propose the Speculative Reward Model (SRM), a plug-and-play framework that seamlessly integrates with existing search strategies. Specifically, SRM employs an external reward assigner to predict optimal actions, reducing reliance on LLMs' internal self-evaluation. And a speculative verification mechanism is used to prune suboptimal choices and guide the search toward more promising steps. We evaluate SRM on several complex decision-making tasks including mathematical reasoning, planning and numerical reasoning in specialized domains. Experimental results show that SRM reduces costs to 1/10 of the original search framework on average while maintaining effectiveness.

Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively

Many challenging reasoning tasks require not just rapid, intuitive responses, but a more deliberate, multi-step approach. Recent progress in large language models (LLMs) highlights an important shift from the “System 1” way of quick reactions to the “System 2” style of reflection-and-correction problem solving. However, current benchmarks heavily rely on the final-answer accuracy, leaving much of a model’s intermediate reasoning steps unexamined. This fails to assess the model’s ability to reflect and rectify mistakes within the reasoning process. To bridge this gap, we introduce FINEREASON, a logic-puzzle benchmark for systematic evaluation of LLMs’ reasoning capabilities. Each puzzle can be decomposed into atomic steps, making it ideal for rigorous validation of intermediate correctness. Building on this, we introduce two tasks: state checking and state transition, for a comprehensive evaluation of how models assess the current situation and plan the next move. To support broader research, we also provide a puzzle training set aimed at enhancing general reasoning. We show that models trained on our state checking and transition data demonstrate gains in mathematical reasoning by up to 5.1%.

FineReason: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving

In the field of urban planning, general-purpose large language models often struggle to meet the specific needs of planners. Tasks like generating urban planning texts, retrieving related information, and evaluating planning documents pose unique challenges. To enhance the efficiency of urban professionals and overcome these obstacles, we introduce PlanGPT, the first specialized AI agent framework tailored for urban and spatial planning. Developed through collaborative efforts with professional urban planners, PlanGPT integrates a customized local database retrieval system, domain-specific knowledge activation capabilities, and advanced tool orchestration mechanisms. Through its comprehensive agent architecture, PlanGPT coordinates multiple specialized components to deliver intelligent assistance precisely tailored to the intricacies of urban planning workflows. Empirical tests demonstrate that PlanGPT framework has achieved advanced performance, providing comprehensive support that significantly enhances professional planning efficiency.

PlanGPT: Enhancing Urban Planning with a Tailored Agent Framework

Exploration, the act of broadening user experiences beyond their established preferences, is challenging in large-scale recommendation systems due to feedback loops and limited signals on user exploration patterns. Large Language Models (LLMs) offer potential solutions by leveraging their world knowledge to recommend novel content outside these loops. A key challenge is aligning LLMs with user preferences while preserving their knowledge and reasoning. To enhance planning for new user interests using LLMs, this paper introduces a novel approach that combines hierarchical planning with LLM inference-time scaling. This method aims to improve recommendation relevancy without compromising novelty. We decouple novelty and user-alignment, training separate LLMs for each objective. We then scale up the novelty-focused LLM's inference and select the best-of-n predictions using the user-aligned LLM. Live experiments demonstrate efficacy, showing significant gains in both user satisfaction (measured by watch activity and active user counts) and exploration diversity.

User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems

Transparency in AI healthcare decision-making
is crucial. By incorporating rationales to explain reason for each predicted label, users
could understand Large Language Models
(LLMs)’s reasoning to make better decision.
In this work, we introduce a new task - Sentiment Reasoning - for both speech and text
modalities, and our proposed multimodal multitask framework and the world’s largest multimodal sentiment analysis dataset. Sentiment Reasoning is an auxiliary task in sentiment analysis where the model predicts both
the sentiment label and generates the rationale behind it based on the input transcript.
Our study conducted on both human transcripts
and Automatic Speech Recognition (ASR) transcripts shows that Sentiment Reasoning helps
improve model transparency by providing rationale for model prediction with quality semantically comparable to humans while also
improving model’s classification performance
(+2% increase in both accuracy and macro-
F1) via rationale-augmented fine-tuning. Also,
no significant difference in the semantic quality of generated rationales between human and
ASR transcripts. All code, data (five languages - Vietnamese, English, Chinese, German, and
French) and models are published online.

Sentiment Reasoning for Healthcare

The integration of generative artificial intelligence into educational applications has enhanced personalized and interactive learning experiences, and it shows strong potential to promote young learners language acquisition. However, it is still challenging to ensure consistent and robust performance across different languages and cultural contexts, and kids-friendly design requires simplified instructions, engaging interactions, and age-appropriate scaffolding to maintain motivation and optimize learning outcomes.
In this work, we introduce SingaKids, a dialogic tutor designed to facilitate language learning through picture description tasks. Our system integrates dense image captioning, multilingual dialogic interaction, speech understanding, and engaging speech generation to create an immersive learning environment in four languages: English, Mandarin, Malay, and Tamil. We further improve the system through multilingual pre-training, task-specific tuning, and scaffolding optimization. Empirical studies with elementary school students demonstrate that SingaKids provides effective dialogic teaching, benefiting learners at different performance levels.

SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning

With the rapid advancement of Large Vision-Language Models (VLMs), concerns about their ‌potential misuse and abuse have grown rapidly. Prior research has exposed VLMs' vulnerability to jailbreak attacks, where carefully crafted inputs can lead the model to produce content that violates ethical and legal standards. However, current jailbreak methods often fail against cutting-edge models such as GPT-4o. We attribute this to the over-exposure of harmful content and the absence of stealthy malicious guidance. 
In this work, we introduce a novel jailbreak framework: Multi-Modal Linkage (MML) Attack. Drawing inspiration from cryptography, MML employs an encryption-decryption process across text and image modalities to mitigate the over-exposure of malicious information. To covertly align the model’s output with harmful objectives, MML leverages a technique we term evil alignment, framing the attack within the narrative context of a video game development scenario. 
Extensive experiments validate the effectiveness of MML. Specifically, MML jailbreaks GPT-4o with attack success rates of 99.40\% on SafeBench, 98.81\% on MM-SafeBench, and 99.07\% on HADES-Dataset. Our code is available at https://github.com/wangyu-ovo/MML.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Federated fine-tuning for Large Language Models (LLMs) has recently gained attention due to the heavy communication overhead of transmitting large model updates. Low Rank Adaptation (LoRA) has been proposed as a solution, yet its application in federated learning is complicated by discordance in aggregation. Existing methods addressing this discordance often suffer from performance degradation at low ranks in heterogeneous data settings. In response, we introduce LoRA-A^2
(Low Rank Adaptation with Alternating freeze and Adaptive rank selection), which demonstrates robustness in challenging settings with low ranks and high data heterogeneity. Our experimental findings reveal that LoRA-A^2
maintains performance even under extreme heterogeneity and low rank conditions, achieving up to a 99.8% reduction in uploaded parameters compared to full fine-tuning without compromising performance. This adaptive mechanism boosts robustness and communication efficiency in federated fine-tuning, enabling the practical deployment of LLMs in resource-constrained environments.

Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients

Social media platforms possess considerable potential in the realm of exploring mental health. Previous research has indicated that major life events can greatly impact individuals' mental health. However, due to the complexity and ambiguity nature of life events, shedding its light on social media data is quite challenging. In this paper, we are dedicated to uncovering life events mentioned in posts on social media. We hereby provide a carefully-annotated social media event dataset, PsyEvent, which encompasses 12 major life event categories that are likely to occur in everyday life. This dataset is human-annotated under iterative procedure and boasts a high level of quality. Furthermore, by applying the life events extracted from posts to downstream tasks such as early risk detection of depression and suicide risk prediction, we have observed a considerable improvement in performance. This suggests that extracting life events from social media can be beneficial for the analysis of individuals' mental health.

Tracking Life’s Ups and Downs: Mining Life Events from Social Media Posts for Mental Health Analysis

We introduce the first set of Universal Dependencies (UD) annotations for Spanish learner writing from the UC Davis COWSL2H corpus. Our annotations include lemmatization, POS tagging, and syntactic dependencies. We adapt the existing UD framework for Spanish L1 to account for learner-specific features such as code-switching and non-canonical syntax. A suite of parsing evaluation experiments shows that parsers trained on learner data together with moderate sizes of Spanish L1 data can yield reasonable performance. Our annotations and parsers will be openly accessible to motivate future development of learner-oriented language technologies.

Downloads

Next from ACL 2025

Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively

Similar lecture

Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training