Austria

Large Language Models (LLMs) are increasingly used in tasks requiring interpretive and inferential accuracy. In this paper, we introduce ExpliCa, a new dataset for evaluating LLMs in explicit causal reasoning. ExpliCa uniquely integrates both causal and temporal relations presented in different linguistic orders and explicitly expressed by linguistic connectives. The dataset is enriched with crowdsourced human acceptability ratings. We tested LLMs on ExpliCa through prompting and perplexity-based metrics. We assessed seven commercial and open-source LLMs, revealing that even top models struggle to reach 0.80 accuracy. Interestingly, models tend to confound temporal relations with causal ones, and their performance is also strongly influenced by the linguistic order of the events. Finally, perplexity-based scores and prompting performance are differently affected by model size.

ACL 2025

ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Models

nlp datasets

evaluation methodologies

language resources

benchmarking

evaluation

### 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

Large Language Models (LLMs) have become powerful tools for algorithm design, leveraging extensive knowledge and contextual reasoning. However, existing methods rely on iterative code generation and performance-based filtering, leading to inefficient exploration and high computational costs. Inspired by butterfly metamorphosis, where organisms undergo structured developmental transitions, Phase I allows larvae to accumulate nutrients, laying the foundation for Phase II, where the pupa transforms into a butterfly. Building on this principle, we introduce Metamorphosis on Prompts (MoP) to iteratively refine task descriptions and Metamorphosis on Algorithms (MoA) to generate more effective solutions. Their nested refinement ensures task-algorithm alignment, systematically improving both task descriptions and algorithmic solutions for more efficient algorithm design. To further enhance efficiency, we incorporate predictor-assisted code evaluation, mimicking natural selection by filtering out weak candidates early and reducing computational costs. Experimental results on TSP, MKP, and CVRP demonstrate that NeRM consistently outperforms state-of-the-art approaches in both performance and efficiency.

Nested-Refinement Metamorphosis: Reflective Evolution of Prompts and Code for Efficient Algorithm Design

Multimodal large language models (MLLMs) are prone to non-factual or outdated knowledge issues, highlighting the importance of knowledge editing. Many benchmark has been proposed for researching multimodal knowledge editing. However, previous benchmarks focus on limited scenarios due to the lack of rigorous definition of multimodal knowledge. To better evaluate multimodal knowledge editing, we propose a decomposed definition of multimodal knowledge. Following the decomposed definition of multimodal knowledge, we introduce three scenarios and a novel requirement modality consistency. We construct MC-MKE, a fine-grained **M**ultimodal **K**nowledge **E**diting benchmark emphasizing **M**odality **C**onsistency through strict data selection. We evaluate four multimodal knowledge editing methods on MC-MKE, revealing their limitations, particularly in terms of modality consistency. Our work highlights the challenges posed by multimodal knowledge editing and motivates further research in developing effective techniques for this task.

MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency

Fine-tuning LLMs with first-order methods like back-propagation is computationally intensive. Zeroth-Order (ZO) optimisation, using function evaluations instead of gradients, reduces memory usage but suffers from slow convergence in high-dimensional models. As a result, ZO research in LLMs has mostly focused on classification, overlooking more complex generative tasks. In this paper, we introduce ZOPrO, a novel ZO algorithm designed for *Preference Optimisation* in LLMs. We begin by analysing the interplay between policy and reward models during traditional (first-order) Preference Optimisation, uncovering patterns in their relative updates. Guided by these insights, we adapt Simultaneous Perturbation Stochastic Approximation (SPSA) with a targeted sampling strategy to accelerate convergence. Through experiments on summarisation, machine translation, and conversational assistants, we demonstrate that our method consistently enhances reward signals while achieving convergence times comparable to first-order methods. While it falls short of some state-of-the-art methods, our work is the first to apply Zeroth-Order methods to Preference Optimisation in LLMs, going beyond classification tasks and paving the way for a largely unexplored research direction.

Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Models

This paper presents a comprehensive evaluation of the capabilities of Large Language Models (LLMs) in metaphor interpretation across multiple datasets, tasks, and prompt configurations. Although metaphor processing has gained significant attention in Natural Language Processing (NLP), previous research has been limited to single-dataset evaluations and specific task settings, often using artificially constructed data through lexical replacement. We address these limitations by conducting extensive experiments using diverse publicly available datasets with inference and metaphor annotations, focusing on Natural Language Inference (NLI) and Question Answering (QA) tasks. The results indicate that LLMs' performance is more influenced by features like lexical overlap and sentence length than by metaphorical content, demonstrating that any alleged emergent abilities of LLMs to understand metaphorical language are the result of a combination of surface-level features, in-context learning, and linguistic knowledge. This work provides critical insights into the current capabilities and limitations of LLMs in processing figurative language, highlighting the need for more realistic evaluation frameworks in metaphor interpretation tasks. Data and code publicly available: https://anonymous.4open.science/r/metaphorLLM-047E/

Metaphor and Large Language Models: When Surface Features Matter More than Deep Understanding

Instruction tuning stands as a crucial advancement in leveraging large language models (LLMs) for enhanced task performance. However, the annotation of instruction datasets has traditionally been expensive and laborious, often relying on manual annotations or costly proprietary LLMs. Recent works explore approaches to synthesize data with open-sourced LLMs but require high-quality human-crafted seed data. In this work, we introduce \mname, an end-to-end framework to synthesize high-quality instruction data with open-sourced LLMs and sampled unlabeled documents, eliminating the necessity for seed data. Starting from diverse pre-screened documents, the framework synthesizes complex and diverse high-quality instruction and response pairs in different stages. We propose a tagging-based prompt method to generate diverse and complex seed data and a UCB-based approach to augment more instruction data with the seed data. A novel \textit{Think Different} prompt is proposed to address the distributional limitations of the seeds, further boosting the data diversity. Experiments prove that the \mname can generate diverse and complex high-quality data even with a opensource small teacher model. The synthesized instruction data demonstrates performance that is comparable to, or even surpasses, baseline annotation methods with proprietary LLMs or open-sourced LLMs while requiring fewer instruction data samples.

FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only

Hyperbolic representations are effective in modeling knowledge graph data which is prevalently used to facilitate multi-hop reasoning. However, a rigorous and detailed comparison of the two spaces for this task is lacking. In this paper, through a simple integration of hyperbolic representations with an encoder-decoder model, we perform a controlled and comprehensive set of experiments to compare the capacity of hyperbolic space versus Euclidean space in multi-hop reasoning. Our results show that the former consistently outperforms the latter across a diverse set of datasets. In addition, through an ablation study, we show that a learnable curvature initialized with the delta hyperbolicity of the utilized data yields superior results to random initializations. Furthermore, our findings suggest a direct correlation between the dataset difficulty, defined as the number of out-going relations in a knowledge graph, and the effectiveness of the hyperbolic space, indicating that hyperbolic representations are more beneficial for harder datasets.

Enhancing Multi-Hop Reasoning for Question Answering with Hyperbolic Representations

Language changes over time, including in the hate speech domain, which evolves quickly following social dynamics and cultural shifts. While NLP research has investigated the impact of language evolution on model training and has proposed several solutions for it, its impact on model benchmarking remains under-explored. Yet, hate speech benchmarks play a crucial role to ensure model safety. In this paper, we empirically evaluate the robustness of 20 language models across two evolving hate speech experiments, and we show the temporal misalignment between static and time-sensitive evaluations. Our findings call for time-sensitive evaluation benchmarks in order to correctly and reliably evaluate language models.

Hatevolution: What Static Benchmarks Don't Tell Us

High-quality instruction data is crucial for developing large language models (LLMs), yet existing approaches struggle to effectively control instruction complexity. We present Tag-Instruct, a novel framework that enhances instruction complexity through structured semantic compression and controlled difficulty augmentation. Unlike previous prompt-based methods operating on raw text, Tag-Instruct compresses instructions into a compact tag space and systematically enhances complexity through RL-guided tag expansion. Through extensive experiments, we show that Tag-Instruct outperforms existing instruction complexity augmentation approaches. Our analysis reveals that operating in tag space provides superior controllability and stability across different instruction synthesis frameworks.

Tag-Instruct: Controlled Instruction Complexity Enhancement through Structure-based Augmentation

Persuasion (or propaganda) techniques detection is a relatively novel task in Natural Language Processing (NLP). While there have already been a number of annotation campaigns, they have been based on heuristic guidelines, which have never been thoroughly discussed. Here, we present the first systematic analysis of a complex annotation task -detecting 22 persuasion techniques in memes-, for which we provided continuous expert oversight. The presence of an expert allowed us to critically analyze specific aspects of the annotation process. Among our findings, we show that inter-annotator agreement alone inadequately assessed annotation correctness. We thus define and track different error types, revealing that expert feedback shows varying effectiveness across error categories. This pattern suggests that distinct mechanisms underlie different kinds of misannotations.
Based on our findings, we advocate for the necessity of expert oversight in annotation tasks and periodic quality audits. In order to reduce the costs for this, we introduce a probabilistic model for optimizing intervention scheduling. To support future research on annotation quality's impact on model performance, we release our comprehensive dataset containing all individual annotator labels, all consolidated annotations, and all expert revisions.

Annotating the Annotators: Analysis, Insights and Modelling from an Annotation Campaign on Persuasion Techniques Detection

Nowadays, news, legislation, guidelines, and corporate reports are discussing the impact of climate change, how to best prevent future damage and adapt to a changing environment. Navigating this wealth of information can be overwhelming for citizens, journalists, legislators, and other stakeholders. Hence, significant efforts have been made in the natural language processing community to facilitate the automatic analysis of a large corpus of text via tasks such as climate-related topic detection, climate risk classification, question answering over climate topics, and many more. In this work, we perform a reproducibility study on 8 tasks and 29 datasets, testing 6 models. Our goal is to highlight potential issues within datasets and evaluation methodologies while also providing cleaned versions of those datasets and a reliable testing platform. We identify in each dataset annotation errors, which can be leveraged to provide new and higher quality datasets. Finally, we release a toolbox containing the cleaned datasets and the evaluation code of models, together with a pipeline for applying the models on corporate documents.

Downloads

Next from ACL 2025

Nested-Refinement Metamorphosis: Reflective Evolution of Prompts and Code for Efficient Algorithm Design

Similar lecture

On the Reliability of Large Language Models for Causal Discovery

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES