Austria

The present popularity of generative language models has amplified interest in interactive methods to guide model outputs. Prompt refinement is considered one of the most effective means to influence output among these methods. We identify several challenges associated with prompting large language models, categorized into data- and model-specific, linguistic, and socio-linguistic challenges. A comprehensive examination of model outputs, including runner-up candidates and their corresponding probabilities, is needed to address these issues. The beam search tree, the prevalent algorithm to sample model outputs, can inherently supply this information. Consequently, we leverage an interactive visual method for investigating the beam search tree, facilitating analysis of the decisions made by the model during generation. Our explorative approach validates existing results and offers additional insights.

ACL 2025

Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges

beam search tree

visualization

large language models

**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).

demo

### 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)

We introduce *Dialz*, a Python library for advancing research on steering vectors for open-source LMs. Steering vectors allow users to modify activations at inference time to amplify or weaken a 'concept', e.g. honesty or positivity, providing a more powerful alternative to prompting or fine-tuning. Dialz supports a diverse set of tasks, including creating contrastive pair datasets, computing and applying steering vectors, and visualizations. Unlike existing libraries, Dialz emphasizes modularity and usability, enabling both rapid prototyping and in-depth analysis. We demonstrate how Dialz can be used to reduce harmful outputs such as stereotypes, while also providing insights into model behaviour across different layers. We release Dialz with full documentation, tutorials, and support for popular open-source models to encourage further research in safe and controllable language generation. Dialz enables faster research cycles and facilitates insights into model interpretability, paving the way for safer, more transparent, and more reliable AI systems.

Dialz: A Python Toolkit for Steering Vectors

In this paper, we present LiDARR (**Li**nking **D**ocument **A**MRs with **R**eferents **R**esolvers), a web tool for semantic annotation at the document level using the formalism of Abstract Meaning Representation (AMR). LiDARR streamlines the creation of comprehensive knowledge graphs from natural language documents through semantic annotation. The tool features a visualization and interactive user interface, transforming document-level AMR annotation into an models-facilitated verification process. This is achieved through the integration of an AMR-to-surface alignment model and a coreference resolution model. Additionally, we incorporate PropBank rolesets into LiDARR to extend implicit roles in annotated AMR, allowing implicit roles to be linked through the coreference chains via AMRs.

LiDARR: Linking Document AMRs with Referents Resolvers

As large language models (LLMs) are gradually integrated into human life, assessing their underlying values becomes essential for understanding their risks and alignment with specific cultural preferences. Despite growing efforts, current value evaluation methods face two key challenges. C1. Evaluation Validity: Static benchmarks fail to reflect intended values or yield informative results due to data contamination or ceiling effect. C2. Result Interpretation: They typically reduce the pluralistic and often incommensurable values to one-dimensional scores, which hinders users from gaining meaningful insights and guidance. To address these challenges, we present Value Compass Leaderboard, the first interactive platform specially devised for comprehensive value diagnosis of LLMs. It (1) grounds evaluations in multiple basic value systems from social science; (2) develops a generative evolving evaluation schema that automatically and dynamically creates real-world test items that co-evolve with ever-advancing LLMs; (3) offers multi-faceted result interpretation, including: (i) fine-grained scores and case studies across 27 value dimensions for 33 leading LLMs, (ii) customized comparisons, and (iii) visualized analysis of LLMs' alignment with cultural values. We hope Value Compass Leaderboard. serves as a navigator for further enhancing LLMs' safety and alignment, further benefiting their responsible and adaptive development.

Value Compass Leaderboard: A Comprehensive, Generative and Self-Evolving Platform for LLMs' Value Evaluation

The computational complexity of large language model (LLM) inference significantly constrains their deployment efficiency on edge devices. In contrast, small language models offer faster decoding and lower resource consumption but often suffer from degraded response quality and heightened susceptibility to hallucinations. To address this trade-off, collaborative decoding, in which a large model assists in generating critical tokens, has emerged as a promising solution. This paradigm leverages the strengths of both model types by enabling high-quality inference through selective intervention of the large model, while maintaining the speed and efficiency of the smaller model. In this work, we present a novel collaborative decoding inference system that allows small models to perform on-device inference while selectively consulting a cloud-based large model for critical token generation. Remarkably, the system achieves a 60\% performance gain on CommonsenseQA using only a 0.5B model on an M1 MacBook, with under 7\% of tokens generation uploaded to the large model in the cloud.

Token Level Routing Inference System for Edge Devices

Step-by-step reasoning is crucial for solving complex visual tasks, yet existing approaches lack a comprehensive framework for evaluating this capability and do not emphasize step-wise problem-solving. To this end, we propose a comprehensive framework for advancing multi-step visual reasoning in large multimodal models (LMMs) through three key contributions. First, we introduce a Visual Reasoning Chain Benchmark, the most comprehensive benchmark for multi-step visual reasoning, covering eight diverse categories and over 4k reasoning steps. This enables rigorous evaluation of LMMs' ability to reason accurately and interpretably across multiple steps. Second, we propose a fine-grained reasoning metric that evaluates correctness and logical coherence at each step, providing deeper insights beyond traditional accuracy metrics. Third, we introduce LlamaV-o1, a state-of-the-art multimodal reasoning model trained using a multi-step curriculum learning approach. LlamaV-o1 is optimized for structured, step-by-step reasoning and significantly outperforms existing open-source models. It surpasses Llava-CoT with a 3.8% absolute gain across six benchmarks, achieving an average score of 67.3 while being 5x
faster during inference scaling. Our benchmark, model, and code is available at https://github.com/mbzuai-oryx/LlamaV-o1.

LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs

Large language models (LLMs) now exhibit near human-level performance in various tasks, but their performance drops drastically after a handful of high-resource languages due to the imbalance in pre-training data. Inspired by the human process of second language acquisition, particularly code-switching---the practice of language alternation in a conversation---we propose code-switching curriculum learning (CSCL) to enhance cross-lingual transfer for LLMs. CSCL mimics the stages of human language learning by progressively training models with a curriculum consisting of 1) token-level code-switching, 2) sentence-level code-switching, and 3) monolingual corpora. Using Qwen 2 as our underlying model, we demonstrate the efficacy of the CSCL in improving language transfer to Korean, achieving significant performance gains compared to monolingual continual pre-training methods. Ablation studies reveal that both token- and sentence-level code-switching significantly enhance cross-lingual transfer and that curriculum learning amplifies these effects. We also extend our findings into various languages, including Japanese (high-resource) and Indonesian (low-resource), and using two additional models (Gemma 2 and Phi 3.5). We further show that CSCL mitigates spurious correlations between language resources and safety alignment, presenting a robust, efficient framework for more equitable language transfer in LLMs. We observe that CSCL is effective for low-resource settings where high-quality, monolingual corpora for language transfer are hardly available.

Code-Switching Curriculum Learning for Multilingual Transfer in LLMs

Current backdoor attack defenders in Natural Language Processing (NLP) typically involve data reduction or model pruning, risking losing crucial information. To address this challenge, we introduce a novel backdoor defender, i.e., BadWindtunnel, in which we build a high-noise simulated training environment, similar to the wind tunnel, which allows precise control over training conditions to model the backdoor learning behavior without affecting the final model. We also use the confidence variance as a learning behavior quantification metric in the simulated training, which is based on the characteristics of backdoor-poisoned data (shorted in poisoned data): higher learnability and robustness. In addition, we propose a two-step strategy to further model poisoned data, including target label identification and poisoned data revealing. Extensive experiments demonstrate BadWindtunnel's superiority, with a 21% higher average reduction in attack success rate than the second-best defender.

BadWindtunnel: Defending Backdoor in High-noise Simulated Training with Confidence Variance

The rapid proliferation of fake news across multiple domains poses significant threats to society. Existing multi-domain detection models typically capture domain-shared semantic features to achieve generalized detection. However, they often fail to generalize well due to poor adaptability, which limits their ability to provide complementary features for detection, especially in data-constrained conditions. To address these challenges, we investigate the propagation-adaptive multi-domain fake news detection paradigm. We propose a novel framework, Structure-adaptive Adversarial Contrastive Learning (StruACL), to adaptively enable structure knowledge transfer between multiple domains. Specifically, we first contrast representations between content-only and propagation-rich data to preserve structural patterns in the shared representation space. Additionally, we design a propagation-guided adversarial training strategy to enhance the diversity of representations. Under the StruACL objective, we leverage a unified Transformer-based and graph-based model to jointly learn transferable semantic and structural features for detection across multiple domains. Experiments on seven fake news datasets demonstrate that StruACL-TGN achieves better multi-domain detection performance on general and data-constrained scenarios, showing the effectiveness and better generalization of StruACL.

Structure-adaptive Adversarial Contrastive Learning for Multi-Domain Fake News Detection

Depression is a widespread mental health disorder, and clinical interviews are the gold standard for assessment. However, their reliance on scarce professionals highlights the need for automated detection. Current systems mainly employ black-box neural networks, which lack interpretability, which is crucial in mental health contexts. Some attempts to improve interpretability use post-hoc LLM generation but suffer from hallucination. To address these limitations, we propose RED, a Retrieval-augmented generation framework for Explainable depression Detection. RED retrieves evidence from clinical interview transcripts, providing explanations for predictions. Traditional query-based retrieval systems use a one-size-fits-all approach, which may not be optimal for depression detection, as user backgrounds and situations vary. We introduce a personalized query generation module that combines standard queries with user-specific background inferred by LLMs, tailoring retrieval to individual contexts. Additionally, to enhance LLM performance in social intelligence, we augment LLMs by retrieving relevant knowledge from a social intelligence datastore using an event-centric retriever. Experimental results on the real-world benchmark demonstrate RED's effectiveness compared to neural networks and LLM-based baselines.

Explainable Depression Detection in Clinical Interviews with Personalized Retrieval-Augmented Generation

The application of role-playing large language models (LLMs) is rapidly expanding in both academic and commercial domains, driving an increasing demand for high-precision role-playing models. Simultaneously, the rapid advancement of reasoning techniques has continuously pushed the performance boundaries of LLMs. This intersection of practical role-playing demands and evolving reasoning capabilities raises an important research question: Can reasoning techniques enhance the role-playing capabilities of LLMs?” To address this, we conduct a comprehensive study using 6 role-playing benchmarks, 24 LLMs, and 3 distinct role-playing strategies, comparing the effectiveness of direct zero-shot role-playing, role-playing with Chain-of-Thought (CoT), and role-playing using reasoning-optimized LLMs. Our findings reveal that CoT may reduce role-playing performance, reasoning-optimized LLMs are unsuitable for role-playing, reasoning ability disrupts the role-playing scaling law, and large models still lack proficiency in advanced role-playing. Furthermore, based on extensive experimental results, we propose two promising future research directions: Role-aware Chain-of-Thought for improving role-playing LLMs and Reinforcement Learning for role-playing LLMs, aiming to enhance the adaptability, consistency, and effectiveness of role-playing LLMs for both research and real-world applications.

Downloads

Next from ACL 2025

Dialz: A Python Toolkit for Steering Vectors

Similar lecture

Determinantal Beam Search