Austria

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.

ACL 2025

Hatevolution: What Static Benchmarks Don&#39;t Tell Us

language change

benchmarks

hate speech

### 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)

Hatevolution: What Static Benchmarks Don't Tell Us

poster

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.

Benchmarking the Benchmarks: Reproducing Climate-Related NLP Tasks

Large language models (LLMs) have advanced conversational AI assistants. However, systematically evaluating how well these assistants apply personalization—adapting to individual user preferences while completing tasks—remains challenging. Existing personalization benchmarks focus on chit-chat, non-conversational tasks, or narrow domains, failing to capture the complexities of personalized task-oriented assistance. To address this, we introduce PersonaLens, a comprehensive benchmark for evaluating personalization in task-oriented AI assistants. Our benchmark features diverse user profiles equipped with rich preferences and interaction histories, along with two specialized LLM-based agents: a user agent that engages in realistic task-oriented dialogues with AI assistants, and a judge agent that employs the LLM-as-a-Judge paradigm to assess personalization, response quality, and task success. Through extensive experiments with current LLM assistants across diverse tasks, we reveal significant variability in their personalization capabilities, providing crucial insights for advancing conversational AI systems.

PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants

Large Language Models have demonstrated outstanding performance across various downstream tasks and have been widely applied in multiple scenarios. Human-annotated preference data is used for training to further improve LLMs' performance, which is constrained by the upper limit of human performance. Therefore, Self-Rewarding method has been proposed, where LLMs generate training data by rewarding their own outputs. However, the existing self-rewarding paradigm is not effective in mathematical reasoning scenarios and may even lead to a decline in performance. In this work, we propose the Process-based Self-Rewarding pipeline for language models, which introduces long-thought reasoning, step-wise LLM-as-a-Judge, and step-wise preference optimization within the self-rewarding paradigm. Our new paradigm successfully enhances the performance of LLMs on multiple mathematical reasoning benchmarks through iterative Process-based Self-Rewarding, demonstrating the immense potential of self-rewarding to achieve artificial intelligence that may surpass human capabilities.

Process-based Self-Rewarding Language Models

Question answering over mixed sources, like text and tables, has been advanced by verbalizing all contents and encoding it with a language model. A prominent case of such heterogeneous data is personal information: user devices log vast amounts of data every day, such as calendar entries, workout statistics, shopping records, streaming history, and more. Information needs range from simple look-ups to queries of analytical nature. The challenge is to provide humans with convenient access with small footprint, so that all personal data stays on the user devices. We present ReQAP, a novel method that creates an executable operator tree for a given question, via recursive decomposition. Operators are designed to enable seamless integration of structured and unstructured sources, and the execution of the operator tree yields a traceable answer. We further release the PerQA benchmark, with persona-based data and questions, covering a diverse spectrum of realistic user needs.

Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data

Language models (LMs) can make a correct prediction based on many possible signals in a prompt, not all corresponding to recall of factual associations. However, current interpretations of LMs fail to take this into account. For example, given the query "Astrid Lindgren was born in" with the corresponding completion "Sweden", no difference is made between whether the prediction was based on knowing where the author was born or assuming that a person with a Swedish-sounding name was born in Sweden. In this paper, we present a model-specific recipe - PrISM - for constructing datasets with examples of four different prediction scenarios: generic language modeling, guesswork, heuristics recall and exact fact recall. We apply two popular interpretability methods to the scenarios: causal tracing (CT) and information flow analysis. We find that both yield distinct results for each scenario. Results for exact fact recall and generic language modeling scenarios confirm previous conclusions about the importance of mid-range MLP sublayers for fact recall, while results for guesswork and heuristics indicate a critical role of late last token position MLP sublayers. In summary, we contribute resources for a more extensive and granular study of fact completion in LMs, together with analyses that provide a more nuanced understanding of how LMs process fact-related queries.

Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion

Despite exceptional capabilities in knowledge-intensive tasks, Large Language Models (LLMs) face a critical gap in understanding how they internalize new knowledge, particularly how acquired knowledge becomes structurally embedded in their neural computations. We address this issue through the lens of knowledge circuit evolution, identifying computational subgraphs that facilitate knowledge storage and processing. Our systematic analysis of circuit evolution throughout continual pre-training reveals several key findings: (1) the acquisition of new knowledge is influenced by its relevance to pre-existing knowledge; (2) the evolution of knowledge circuits exhibits a distinct phase shift from formation to optimization; (3) the evolution of knowledge circuits follows a deep-to-shallow pattern. These insights not only advance our theoretical understanding of the mechanisms of new knowledge acquisition in LLMs, but also provide potential implications for improving continual pre-training strategies to enhance model performance.

How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training

Temporal tabular question answering presents a significant challenge for Large Language Models (LLMs), requiring robust reasoning over structured data—a task where traditional prompting methods often fall short. These methods face challenges such as memorization, sensitivity to table size, and reduced performance on complex queries. To overcome these limitations, we introduce TEMPTABQA-C, a synthetic dataset designed for systematic and controlled evaluations, alongside a symbolic intermediate representation that transforms tables into database schemas. This structured approach allows LLMs to generate and execute SQL queries, enhancing generalization and mitigating biases. By incorporating adaptive fewshot prompting with contextually tailored examples, our method achieves superior robustness, scalability, and performance. Experimental results consistently highlight improvements across key challenges, setting a new benchmark for robust temporal reasoning with LLMs.

LLM-Symbolic Integration for Robust Temporal Tabular Reasoning

Large language models (LLMs) have transformed AI across diverse domains, with prompting being central to their success in guiding model outputs. However, manual prompt engineering is both labor-intensive and domain-specific, necessitating the need for automated solutions. We introduce PromptWizard, a novel, fully automated framework for discrete prompt optimization, utilizing a self-evolving, self-adapting mechanism. Through a feedback-driven critique and synthesis process, PromptWizard achieves an effective balance between exploration and exploitation, iteratively refining both prompt instructions and in-context examples to generate human-readable, task-specific prompts. This guided approach systematically improves prompt quality, resulting in superior performance across 45 tasks. PromptWizard excels even with limited training data, smaller LLMs, and various LLM architectures. Additionally, our cost analysis reveals a substantial reduction in API calls, token usage, and overall cost, demonstrating PromptWizard's efficiency, scalability, and advantages over existing prompt optimization strategies.

Downloads

Next from ACL 2025

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

Similar lecture

Hatevolution: What Static Benchmarks Don't Tell Us