Austria

We explore large language model (LLM) responses that may negatively impact the transgender and nonbinary (TGNB) community and introduce the Transing Transformers Toolkit, $T^3$, which provides resources for identifying such harmful response behaviors. The heart of $T^3$ is a community-centred taxonomy of harms, developed in collaboration with the TGNB community, which we complement with, amongst other guidance, suggested heuristics for evaluation. To develop the taxonomy, we adopted a multi-method approach that included surveys and focus groups with community experts. The contribution highlights the importance of community-centred approaches in mitigating harm, and outlines pathways for LLM developers to improve how their models handle TGNB-related topics.

ACL 2025

Amplifying Trans and Nonbinary Voices: A Community-Centred Harm Taxonomy for LLMs

harms

transgender

community

taxonomy

Welcome to the **largest national, multi-specialty research** event featuring research from nearly 700 medical students, residents, fellows, and international medical graduates.

Use the buttons below or navigation menu to access the event.
 


[![](https://assets.underline.io/uploads/markdown_image/1/image/3e33a8c754cc49610b30950617d813e7.png)](https://underline.io/events/434/sessions?searchGroup=all)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/551404d429c4e274f9a54cbdd7081918.png)](https://underline.io/events/434/posters?searchGroup=all)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/677d92f566b880cebd36905fc738fc10.png)](https://underline.io/events/434/lounge)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/c7392833c7261c3874c5b43fa2f4df19.png)](https://underline.io/events/434/help-desk)
 

#### Event Details

The 2023 American Medical Association Research Challenge includes a poster symposium hall and a semifinals hall with the top scored research. **Log in at any time throughout the event to:**

* **View posters and presentations** on a variety of topics and specialties
* **Score posters in the semifinals** to help decide the top five finalists (AMA member exclusive opportunity)
* **Connect with participants** and provide feedback to help advance their research
* **Attend education sessions** with physician experts on key research topics

At the conclusion of this event, the AMA will announce the top five finalists who will advance to the AMA Research Challenge finals, present their research to an elite panel of judges, and compete to win a $10,000 grand prize sponsored by Laurel Road. 

### Grand Prize Sponsor

AMA would like to thank Laurel Road for sponsoring a $10,000 grand prize for the winner of the AMA Research Challenge. Laurel Road is not involved in the judging or scoring process to select the winner. The winner will be announced on February 4, 2024 during the AMA Research Challenge finals. Payment of the grand prize will be directly from Laurel Road. See the AMA Research Challenge Official Rules for terms and conditions.

![](https://assets.underline.io/uploads/markdown_image/1/image/611e331d4a0eba0920f240cfc04b4d77.png)

**There is no registration fee for this event! **

Register to explore research in a variety of topics. AMA members get exclusive access to score posters in the semifinals.

**Please use this link [here](https://www.ama-assn.org/about/events/ama-research-challenge) to register for free.**

Registration Is Required

AMA Research Challenge 2023

Join the AMA Research Challenge poster symposium and semifinals to explore top research posters, score posters in the semifinals (an AMA member exclusive opportunity) and attend education sessions with experienced physicians to learn tips to advance your research and career. 

technical paper

### 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)

Recently, o1-like models have drawn significant attention, where these models produce the long Chain-of-Thought (CoT) reasoning steps to improve the reasoning abilities of existing Large Language Models (LLMs). In this paper, to understand the qualities of these long CoTs and measure the critique abilities of existing LLMs on these long CoTs, we introduce the DeltaBench including the generated long CoTs from different o1-like models (e.g., QwQ, DeepSeek-R1) for different reasoning tasks (e.g., Math, Code, General Reasoning), to measure the ability to detect errors in long COT reasoning. Based on DeltaBench, we first perform fine-grained analysis of the generated long CoTs to discover the effectiveness and efficiency of different o1-like models. Then, we conduct extensive evaluations of existing process reward models (PRMs) and critic models to detect the errors of each annotated process, which aims to investigate the boundaries and limitations of existing PRMs and critic models. Finally, we hope that DeltaBench could guide developers to better understand the long CoT reasoning abilities of their models.

Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?

Semantic Text Embedding is a fundamental NLP task that encodes textual content into vector representations, where proximity in the embedding space reflects semantic similarity. While existing embedding models excel at capturing general meaning, they often overlook ideological nuances, limiting their effectiveness in tasks that require an understanding of political bias. To address this gap, we introduce \algo{PRISM}, the first framework designed to \textbf{P}roduce inte\textbf{R}pretable pol\textbf{I}tical bia\textbf{S} e\textbf{M}beddings. \algo{PRISM} operates in two key stages: (1) Controversial Topic Bias Indicator Mining, which systematically extracts fine-grained political topics and corresponding bias indicators from weakly labeled news data, and (2) Cross-Encoder Political Bias Embedding, which assigns structured bias scores to news articles based on their alignment with these indicators. This approach ensures that embeddings are explicitly tied to bias-revealing dimensions, enhancing both interpretability and predictive power. Through extensive experiments on large-scale datasets, we demonstrate that \algo{PRISM} outperforms state-of-the-art text embedding models in political bias classification while offering highly interpretable representations that facilitate diversified retrieval and ideological analysis. The source code is available at \url{https://anonymous.4open.science/r/PRISM-80B4/}.

PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encoder

Current LLM pipelines account for only one possible tokenization for a given string, ignoring exponentially many alternative tokenizations during training and inference. For example, the standard Llama3 tokenization of penguin is [p,enguin], yet [peng,uin] is another perfectly valid alternative. In this paper, we show that despite LLMs being trained solely on one tokenization, they still retain semantic understanding of other tokenizations, raising questions about their implications in LLM safety. Put succinctly, we answer the following question: can we adversarially tokenize an obviously malicious string to evade safety and alignment restrictions? We show that not only is adversarial tokenization an effective yet previously neglected axis of attack, but it is also competitive against existing state-of-the-art adversarial approaches without changing the text of the harmful request. We empirically validate this exploit across three state-of-the-art LLMs and adversarial datasets, revealing a previously unknown vulnerability in subword models.

Adversarial Tokenization

Text-to-speech (TTS) technology has achieved impressive results for widely spoken languages, yet many under-resourced languages remain challenged by limited data and linguistic complexities. In this paper, we present a novel methodology that integrates a data-optimized framework with an advanced acoustic model to build high-quality TTS systems for low-resource scenarios. We demonstrate the effectiveness of our approach using Thai as an illustrative case, where intricate phonetic rules and sparse resources are effectively addressed. Our method enables zero-shot voice cloning and improved performance across diverse client applications, ranging from finance to healthcare, education, and law. Extensive evaluations—both subjective and objective—confirm that our model meets state-of-the-art standards, offering a scalable solution for TTS production in data-limited settings, with significant implications for broader industry adoption and multilingual accessibility. All demos are available in \url{https://luoji.cn/static/thai/demo.html}.

Scaling Under-Resourced TTS: A Data-Optimized Framework with Advanced Acoustic Modeling for Thai

Word-by-word language model surprisal is often used to model the incremental processing of human readers, which raises questions about how various choices in language modeling influence its predictive power. One factor that has been overlooked in cognitive modeling is the granularity of subword tokens, which explicitly encodes information about word length and frequency, and ultimately influences the quality of vector representations that are learned. This paper presents experiments that manipulate the token granularity and evaluate its impact on the ability of surprisal to account for processing difficulty of naturalistic text and garden-path constructions. Experiments with naturalistic reading times reveal a substantial influence of token granularity on surprisal, with tokens defined by a vocabulary size of 8,000 resulting in surprisal that is most predictive. In contrast, on garden-path constructions, language models trained on coarser-grained tokens generally assigned higher surprisal to critical regions, suggesting a greater sensitivity to garden-path effects than previously reported. Taken together, these results suggest a large role of token granularity on the quality of language model surprisal for cognitive modeling.

The Impact of Token Granularity on the Predictive Power of Language Model Surprisal

This paper explores the effectiveness of Multimodal Large Language models (MLLMs) as assistive technologies for visually impaired individuals. We conduct a user survey to identify adoption patterns and key challenges users face with such technologies. Despite a high adoption rate of these models, our findings highlight concerns related to contextual understanding, cultural sensitivity, and complex scene understanding, particularly for individuals who may rely solely on them for visual interpretation. Informed by these results, we collate five user-centred tasks with image and video inputs, including a novel task on Optical Braille Recognition. Our systematic evaluation of twelve MLLMs reveals that further advancements are necessary to overcome limitations related to cultural context, multilingual support, Braille reading comprehension, assistive object recognition, and hallucinations. This work provides critical insights into the future direction of multimodal AI for accessibility, underscoring the need for more inclusive, robust, and trustworthy visual assistance technologies.

Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users

The multilingual neural machine translation (MNMT) aims for arbitrary translations across multiple languages.
Although MNMT-specific models trained on parallel data offer low costs in training and deployment, their performance consistently lags behind that of large language models (LLMs).
In this work, we introduce registering, a novel method that enables a small MNMT-specific model to compete with LLMs.
Specifically, we insert a set of artificial tokens specifying the target language, called registers, into the input sequence between the source and target tokens.
By modifying the attention mask, the target token generation only pays attention to the activation of registers, representing the source tokens in the target language space.
Experiments on EC-40, a large-scale benchmark, show that our method advances the state-of-the-art of MNMT.
We further pre-train two models, namely MITRE (multilingual translation with registers), by 9.3 billion sentence pairs across 24 languages collected from public corpora.
One of them, MITRE-913M, outperforms NLLB-3.3B, achieves comparable performance with commercial LLMs, and shows strong adaptability in fine-tuning.
Finally, we open-source our models to facilitate further research and development in MNMT: https://github.com/zhiqu22/mitre.

Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translation

Modeling relationships between concepts and entities is essential for many applications. While Large Language Models (LLMs) capture relational and commonsense knowledge effectively, they are computationally expensive and often underperform in tasks requiring efficient relational encoding, such as relation induction, extraction, and information retrieval. Despite advancements in learning relational embeddings, existing methods often fail to capture nuanced representations and the rich semantics needed for high-quality embeddings. In this work, we propose different relational encoders designed to capture diverse relational aspects and semantic properties of entity pairs. Although several datasets exist for training such encoders, they often rely on structured knowledge bases or predefined schemas, which primarily encode simple and static relations. To overcome this limitation, we also introduce a novel dataset generation method leveraging LLMs to create a diverse spectrum of relationships. Our experiments demonstrate the effectiveness of our proposed encoders and the benefits of our generated dataset.

Modelling Complex Semantics Relation with Contrastively Fine-Tuned Relational Encoders

Identifying arguments is a necessary prerequisite for various tasks in automated discourse analysis, particularly within contexts such as political debates, online discussions, and scientific reasoning. In addition to theoretical advances in understanding the constitution of arguments, a significant body of research has emerged around practical argument mining, supported by a growing number of publicly available datasets. On these benchmarks, BERT-like transformers have consistently performed best, reinforcing the belief that such models are broadly applicable across diverse contexts of debate. This study offers the first large-scale re-evaluation of such state-of-the-art models, with a specific focus on their ability to generalize in identifying arguments. We evaluate four transformers, three standard and one enhanced with contrastive pre-training for better generalization, on 17 English sentence-level datasets as most relevant to the task. Our findings show that, to varying degrees, these models tend to rely on lexical shortcuts tied to content words, suggesting that apparent progress may often be driven by dataset-specific cues rather than true task alignment. While the models achieve strong results on familiar benchmarks, their performance drops markedly when applied to unseen datasets. Nonetheless, incorporating both task-specific pre-training and joint benchmark training proves effective in enhancing both robustness and generalization.

Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments

Most Large Vision-Language Models (LVLMs) to date are trained predominantly on English data, which makes them struggle to understand non-English input and fail to generate output in the desired target language. Existing efforts mitigate these issues by adding multilingual training data, but do so in a largely ad-hoc manner, lacking insight into how different training mixes tip the scale for different groups of languages. In this work, we present a comprehensive investigation into the training strategies for massively multilingual LVLMs. First, we conduct a series of multi-stage experiments spanning 13 downstream vision-language tasks and 43 languages, systematically examining: (1) the number of training languages that can be included without degrading English performance and (2) optimal language distributions of pre-training as well as (3) instruction-tuning data. Further, we (4) investigate how to improve multilingual text-in-image understanding, and introduce a new benchmark for the task. Surprisingly, our analysis reveals that one can (i) include as many as 100 training languages simultaneously (ii) with as little as 25-50% of non-English data, to greatly improve multilingual performance while retaining strong English performance. We further find that (iii) including non-English OCR data in pre-training and instruction-tuning is paramount for improving multilingual text-in-image understanding. Finally, we put all our findings together and train \modelname, a 100-language LVLM, offering state-of-the-art performance in an evaluation covering 14 tasks and 56 languages.

Downloads

Next from ACL 2025

Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?

Similar lecture

Prevalence of Cardiac Arrhythmias in Transgender and Nonbinary Community Adult Health Center Patients