Austria

Human activity is moderated by norms. However, machines are often trained without explicit supervision on norm understanding and reasoning, especially when the norms are grounded in a physical and social context. To improve and evaluate the normative reasoning capability of vision-language models (VLMs), we present EgoNormia, consisting of 1,853 ego-centric videos of human interactions, each of which has two related questions evaluating both the prediction and justification of normative actions. The normative actions encompass seven categories: safety, privacy, proxemics, politeness, cooperation, coordination/proactivity, and communication/legibility. To compile this dataset at scale, we propose a novel pipeline leveraging video sampling, automatic answer generation, filtering, and human validation. Our work demonstrates that current state-of-the-art vision-language models lack robust norm understanding, scoring a maximum of 54% on EgoNormia (versus a human bench of 92%). Our analysis of performance in each dimension highlights the significant risks of safety, privacy, and the lack of collaboration and communication capability when applied to real-world agents. We additionally show that through a retrieval-based generation method, it is possible to use EgoNormia to enhance normative reasoning in VLMs.

ACL 2025

EgoNormia: Benchmarking Physical Social Norm Understanding

robotics and beyond

multimodality and language grounding to vision

human-centered nlp

resources and evaluation

question answering

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). The aim of the joint conference is to provide a single, high-profile, internationally-respected archival forum for scientific research in the theory and practice of autonomous agents and multi-agent systems.

Browse keynotes, discussions, panels and over 300 presentations.


AAMAS 2020

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). 

poster

### 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)

This study proposes a simple yet effective LoRA merge method to achieve LLM adaptation for low-resource language generation tasks. The LoRA merge technique, which integrates multiple LoRA modules trained on different tasks, has gained attention as an effective and efficient approach for adapting LLMs to target tasks. However, previous methods are limited in adaptability as they keep the LoRA parameters frozen. Additionally, the low-resource problem has been out of their scope. We propose a LoRA merge method that updates LoRA parameters during the merge process to improve task-specific adaptability. Furthermore, we further enhance the adaptability by parameter pruning that allows finer-grained adjustments of LoRA parameters during merging. Extensive experiments have been conducted taking summarization as a benchmark task. Our datasets cover various domains and multiple languages of English and Japanese. The results confirm that the proposed method achieves significant and consistent improvements in task adaptability over the previous methods.

Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation

Speculative decoding (SD) accelerates Large Language Model (LLM) generation by using an efficient draft model to propose the next few tokens, which are verified by the LLM in a single forward call, reducing latency while preserving its outputs. We focus on retrieval-based SD where the draft model retrieves the next tokens from a non-parametric datastore. Sparse retrieval \cite[REST], which operates on the surface form of strings, is currently the dominant paradigm due to its simplicity and scalability. However, its effectiveness is limited due to the usage of short contexts and exact string matching. Instead, we introduce Dense Retrieval for Speculative Decoding (DReSD), a novel framework that uses approximate nearest neighbour search with contextualised token embeddings to retrieve the most semantically relevant token sequences for SD. Extensive experiments show that DReSD achieves (on average) 87% higher acceptance rates, 65% longer accepted tokens and 19% faster generation speeds compared to sparse retrieval (REST).

DReSD: Dense Retrieval for Speculative Decoding

Self-consistency decoding enhances LLMs' performance on reasoning tasks by sampling diverse reasoning paths and selecting the most frequent answer. However, it is computationally expensive, as sampling many of these (lengthy) paths is required to increase the chances that the correct answer emerges as the most frequent one. To address this, we introduce Confidence-Informed Self-Consistency (CISC). CISC performs a weighted majority vote based on confidence scores obtained directly from the model. By prioritizing high-confidence paths, it can identify the correct answer with a significantly smaller sample size. When tested on nine models and four datasets, CISC outperforms self-consistency in nearly all configurations, reducing the required number of reasoning paths by over 40% on average. In addition, we introduce the notion of within-question confidence evaluation, after showing that standard evaluation methods are poor predictors of success in distinguishing correct and incorrect answers to the same question. In fact, the most calibrated confidence method proved to be the least effective for CISC. Lastly, beyond these practical implications, our results and analyses show that LLMs can effectively judge the correctness of their own outputs, contributing to the ongoing debate on this topic.

Confidence Improves Self-Consistency in LLMs

Multimodal large language models (MLLMs) have shown remarkable capabilities across various downstream tasks. However, when MLLMs are transferred to the text image machine translation (TiMT) task, preliminary experiments reveal that MLLMs suffer from serious repetition and omission hallucinations. To alleviate these issues, this paper first designs an efficient MLLM named InImageTrans for TiMT and then proposes a simple and effective method named multi-conditional direct preference optimization (mcDPO) for advancing the TiMT. Particularly, the proposed mcDPO not only guides the MLLM in rejecting repetition output by creating text output preference pairs automatically, but also guides the MLLM in paying more attention to text information in images by creating image input preference pairs. Furthermore, we build a high-quality benchmark called MCiT for comprehensively evaluating the TiMT capabilities of InImageTrans. Experimental results show that the proposed method significantly outperforms existing open-source MLLMs on MCiT. All data and codes will be released once accepted.

InImageTrans: Multimodal LLM-based Text Image Machine Translation

Model routing allocates queries to the suitable model, improving system performance while reducing costs. However, existing routing methods face practical limitations that hinder scalability in large-scale applications and struggle to keep up with the rapid growth of the large language model (LLM) ecosystem. To tackle these challenges, we propose TagRouter, a training-free model routing method designed to optimize the synergy among multiple LLMs for open-domain text generation tasks. Experimental results demonstrate that TagRouter outperforms 13 baseline methods, increasing the accept rate of system by 6.15% and reducing costs by 17.20%, achieving optimal cost-efficiency. Our findings provides the LLM community with an efficient and scalable solution for model ensembling, offering users an evolvable "super model."

TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks

The development of autonomous agents increasingly relies on Multimodal Language Models (MLMs) to perform tasks described in natural language with GUI environments, such as websites, desktop computers, or mobile phones. Existing benchmarks for MLM agents in interactive environments are limited by their focus on a single environment, lack of detailed and generalized evaluation methods, and the complexities of constructing tasks and evaluators. To overcome these limitations, we introduce CRAB, the first cross-environment agent benchmark framework, incorporating a graph-based fine-grained evaluation method and an efficient task generation method. Our framework supports multiple devices and can be easily extended to any environment with a Python interface. Leveraging CRAB, we develope CRAB Benchmark-v0 comprising 120 tasks in computer desktop and mobile phone environments. We evaluated 6 advanced MLMs using different single and multi-agent system configurations on this benchmark. The experimental results demonstrate that the single agent with GPT-4o achieves the best completion ratio of 38.01%.

CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents

Current exploration on creative generation focuses mainly on short stories, poetry, and scripts. With the expansion of Large Language Models (LLMs) context windows, "novel" avenues emerge. This study aims to extend the boundaries of Natural Language Generation (NLG) evaluation by exploring LLMs' capabilities in more challenging long-form fiction. We propose a new multi-level evaluation framework that incorporates ten metrics across the Macro, Meso, and Micro levels. An annotated fiction dataset, sourced from human authors, LLMs, and human-AI collaborations in both English and Chinese is then constructed. Human evaluation reveals notable disparities between LLM-generated and human-authored fictions, particularly the “high-starting, low-ending” pattern in LLM outputs. We further probe ten high-performing LLMs through different prompt templates, achieving moderate correlations by strategically utilizing diverse LLMs tailored to different levels, as an initial step towards better automatic fiction evaluation. Finally, we offer a fine-grained analysis of LLMs capabilities through six issues, providing promising insights for future advancements.

Towards A “Novel” Benchmark: Evaluating Literary Fiction with Large Language Models

Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Current approaches either assemble specialized expert models or directly generate page-level content autoregressively, facing integration overhead, efficiency bottlenecks, and layout structure degradation despite their decent performance. To address these limitations, we present Dolphin ( Document Image Parsing via Heterogeneous Anchor Prompting), a novel multimodal document image parsing model following an analyze-then-parse paradigm. In the first stage, Dolphin generates a sequence of layout elements in reading order. These heterogeneous elements, serving as anchors and coupled with task-specific prompts, are fed back to Dolphin for parallel content parsing in the second stage. To train Dolphin, we construct a large-scale dataset of over 30 million samples, covering multi-granularity parsing tasks. Through comprehensive evaluations on both prevalent benchmarks and self-constructed ones, Dolphin achieves state-of-the-art performance across diverse page-level and element-level settings, while ensuring superior efficiency through its lightweight architecture and parallel parsing mechanism. The code and pre-trained models are publicly available at https://github.com/ByteDance/Dolphin

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting

Augmenting large language models (LLMs) with external context significantly improves their performance in natural language processing (NLP) tasks. However, LLMs struggle to answer queries reliably when the provided context lacks information, often resorting to ungrounded speculation or internal knowledge. Groundedness – generating responses strictly supported by the context – is essential for ensuring factual consistency and trustworthiness. This study focuses on detecting whether a given query is grounded in a document provided in context before the costly answer generation by LLMs. Such a detection mechanism can significantly reduce both inference time and resource consumption. We show that lightweight, task-specific encoder models such as RoBERTa and NomicBERT, fine-tuned on curated datasets, can achieve accuracy comparable to state-of-the-art LLMs, such as Llama3 8B and GPT4o, in groundedness detection while reducing inference latency by orders of magnitude.

Small Encoders Can Rival Large Decoders in Detecting Groundedness

With the growing adoption of Retrieval-Augmented Generation (RAG) in document processing, robust text recognition has become increasingly critical for knowledge extraction. While OCR (Optical Character Recognition) for English and other languages benefits from large datasets and well-established benchmarks, Arabic OCR faces unique challenges due to its cursive script, right-to-left text flow, and complex typographic and calligraphic features. We present KITAB-Bench, a comprehensive Arabic OCR benchmark that fills the gaps in current evaluation systems. Our benchmark comprises 8,809 samples across 9 major domains and 36 sub-domains, encompassing diverse document types including handwritten text, structured tables, and specialized coverage of 21 chart types for business intelligence. Our findings show that modern vision-language models (such as GPT-4, Gemini, and Qwen) outperform traditional OCR approached (like EasyOCR, PaddleOCR, and Surya) by an average of 60% in Character Error Rate (CER). Furthermore, we highlight significant limitations of current Arabic OCR models, particularly in PDF-to-Markdown conversion, where the best model Gemini-2.0-Flash achieves only 65% accuracy. This underscores the challenges in accurately recognizing Arabic text, including issues with complex fonts, numeral recognition errors, word elongation, and table structure detection. This work establishes a rigorous evaluation framework that can drive improvements in Arabic document analysis methods and bridge the performance gap with English OCR technologies.

Downloads

Next from ACL 2025

Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation

Similar lecture

Norm Emergence in Multiagent Systems: A Viewpoint Paper