Mexico

Without proper safeguards, large language models will readily follow malicious instructions and generate toxic content. This risk motivates safety efforts such as red-teaming and large-scale feedback learning, which aim to make models both helpful and harmless. However, there is a tension between these two objectives, since harmlessness requires models to refuse to comply with unsafe prompts, and thus not be helpful. Recent anecdotal evidence suggests that some models may have struck a poor balance, so that even clearly safe prompts are refused if they use similar language to unsafe prompts or mention sensitive topics. In this paper, we introduce a new test suite called XSTest to identify such eXaggerated Safety behaviours in a systematic way. XSTest comprises 250 safe prompts across ten prompt types that well-calibrated models should not refuse to comply with, and 200 unsafe prompts as contrasts that models, for most applications, should refuse. We describe XSTest&#39;s creation and composition, and then use the test suite to highlight systematic failure modes in state-of-the-art language models as well as more general challenges in building safer language models.

NAACL 2024

XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

false refusal

safety

large language models

evaluation

dataset

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Without proper safeguards, large language models will readily follow malicious instructions and generate toxic content. This risk motivates safety efforts such as red-teaming and large-scale feedback learning, which aim to make models both helpful and harmless. However, there is a tension between these two objectives, since harmlessness requires models to refuse to comply with unsafe prompts, and thus not be helpful. Recent anecdotal evidence suggests that some models may have struck a poor balance, so that even clearly safe prompts are refused if they use similar language to unsafe prompts or mention sensitive topics. In this paper, we introduce a new test suite called XSTest to identify such eXaggerated Safety behaviours in a systematic way. XSTest comprises 250 safe prompts across ten prompt types that well-calibrated models should not refuse to comply with, and 200 unsafe prompts as contrasts that models, for most applications, should refuse. We describe XSTest's creation and composition, and then use the test suite to highlight systematic failure modes in state-of-the-art language models as well as more general challenges in building safer language models.

poster

## Welcome to 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics!
This year, the conference is in Mexico City. NAACL was actually already planned for Mexico City in 2021, but due to the pandemic the entire conference was moved online. This year, finally, we get to go! So it is my sincere pleasure to welcome you to Mexico City, whether in person or virtually. Having the conference in Mexico City is a good opportunity to emphasize that NAACL is our flagship conference for ACL members not only in North America but also in Central and South America, even though NAACL has been bearing “North” in its name. At this year’s conference, we have a theme to match, with a theme track on the Languages of Latin America to showcase the linguistic diversity of the region.
 
The opportunity to present at NAACL should not depend on a researcher’s travel budget, or their family status. This is why it is so important to make virtual participation at NAACL as good an experience as possible – but we want to also provide a good experience for in-person participants. As a community, we are still working out the best way to do that. This year at NAACL, we are trying out a big virtual poster session ahead of the conference, with the hope that this will make make for a lively and interactive experience. At the same time, we are reducing virtual oral presentations, which seem to be particularly tricky to make to work well. A big thanks to the NAACL program chairs and to Luciana Benotti for all their ideas and work to improve the virtual experience. And participants, virtual as well as in-person: Please let us know what worked for you and what didn’t, so we can continue to improve hybrid conferences. 
 
I have been lucky to work with many amazing people. Without their insight, dedication and patience, and without the many hours of work they put in, NAACL would not have been possible. A huge thank you to the program chairs Helena Gomez, Kevin Duh, and Steve Bethard – you are the best! 
 
Finally, I would like to thank all authors, invited speakers and panelists, area chairs and reviewers, the volunteers organizing and chairing sessions, and all attendees, in-person and virtual. Thank you for helping us make NAACL 2024 come to life. 
 
Welcome and hope you all enjoy the conference! 
Katrin Erk 
The University of Texas at Austin 
NAACL-2024 General Chair 
*You can read the full Welcome message in the [Conference Handbook (downloadable)](https://drive.google.com/file/d/1H1NvW0VASQjkSCYgw3mr-3l4yYDSxz6B/view?usp=sharing)*

To access the event page you need to register [**here.**](http://acl.swoogo.com/naacl2024) 
Your access to the event page is limited based on your registration type. If you registered for workshops only, you will gain access to full workshops content on the day of the workshops program.

Please register!

2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics

The Mayan languages comprise a language family with an ancient history, millions of speakers, and immense cultural value, that, nevertheless, remains severely underrepresented in terms of resources and global exposure. In this paper we develop, curate, and publicly release a set of corpora in several Mayan languages spoken in Guatemala and Southern Mexico, which we call MayanV. The datasets are parallel with Spanish, the dominant language of the region, and are taken from official native sources focused on representing informal, day-to-day, and non-domain-specific language. As such, and according to our dialectometric analysis, they differ in register from most other available resources. Additionally, we present neural machine translation models, trained on as many resources and Mayan languages as possible, and evaluated exclusively on our datasets. We observe lexical divergences between the dialects of Spanish in our resources and the more widespread written standard of Spanish, and that resources other than the ones we present do not seem to improve translation performance, indicating that many such resources may not accurately capture common, real-life language usage. The MayanV dataset is available at https://github.com/transducens/mayanv.

Curated Datasets and Neural Models for Machine Translation of Informal Registers between Mayan and Spanish Vernaculars

In recent times, large language models (LLMs) have shown impressive performance on various document-level tasks such as document classification, summarization, and question-answering. However, research on understanding their capabilities on the task of self-contradictions in long documents has been very limited. In this work, we introduce ContraDoc, the first human-annotated dataset to study self-contradictions in long documents across multiple domains, varying document lengths, self-contradiction types, and appearance scope. We then analyze the current capabilities of four state-of-the-art open-source and commercially available LLMs: GPT3.5, GPT4, PaLM2, and LLaMAv2 on this dataset. While GPT4 performs the best and can outperform humans on this task, we find that it is still unreliable and struggles with self-contradictions that require more nuance and context. We release the dataset and all the code associated with the experiments.

ContraDoc: Understanding Self-Contradictions in Documents with Large Language Models

Babel Briefings is a novel dataset featuring 4.7 million news headlines from August 2020 to November 2021, across 30 languages and 54 locations worldwide with English translations of all articles included. Designed for natural language processing and media studies, it serves as a high-quality dataset for training or evaluating language models as well as offering a simple, accessible collection of articles, for example, to analyze global news coverage and cultural narratives. As a simple demonstration of the analyses facilitated by this dataset, we use a basic procedure using a TF-IDF weighted similarity metric to group articles into clusters about the same event. We then visualize the \emph{event signatures} of the event showing articles of which languages appear over time, revealing intuitive features based on the proximity of the event and unexpectedness of the event. The dataset is available on [Kaggle](https://www.kaggle.com/datasets/felixludos/babel-briefings) and [HuggingFace](https://huggingface.co/datasets/felixludos/babel-briefings) with accompanying [GitHub](https://github.com/felixludos/babel-briefings) code.

A diverse Multilingual News Headlines Dataset from around the World

Conversational moderation of online communities is crucial to maintaining civility for a constructive environment, but it is challenging to scale and harmful to moderators. The inclusion of sophisticated natural language generation modules as a force multiplier to aid human moderators is a tantalizing prospect, but adequate evaluation approaches have so far been elusive. In this paper, we establish a systematic definition of conversational moderation effectiveness grounded on moderation literature and establish design criteria for conducting realistic yet safe evaluation. We then propose a comprehensive evaluation framework to assess models' moderation capabilities independently of human intervention. With our framework, we conduct the first known study of language models as conversational moderators, finding that appropriately prompted models that incorporate insights from social science can provide specific and fair feedback on toxic behavior but struggle to influence users to increase their levels of respect and cooperation.

Can Language Model Moderators Improve the Health of Online Discourse?

Despite the high performances of large language models (LLMs) across numerous benchmarks, recent research has unveiled their suffering from hallucinations and unfaithful reasoning. This work studies a type of hallucination induced by semantic associations. We investigate to what extent LLMs take shortcuts from certain keyword/entity biases in the prompt instead of following correct reasoning paths. To quantify this phenomenon, we propose a novel probing method and benchmark called EUREQA. EUREQA is an entity-searching task where a model finds a missing entity based on described multi-hop relations with other entities. These deliberately designed multi-hop relations create deceptive semantic associations, and models must stick to the correct reasoning path instead of incorrect shortcuts to find the correct answer. Experiments show that existing LLMs cannot follow correct reasoning paths and resist the attempt of greedy shortcuts, with GPT-4 only achieving 62\% accuracy. Analyses provide further evidence that LLMs rely on semantic biases to solve the task instead of proper reasoning, questioning the validity and generalizability of current LLMs' high performances.

Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?

We assemble a broad Natural Language Understanding benchmark suite for the German language and consequently evaluate a wide array of existing German-capable models in order to create a better understanding of the current state of German LLMs. Our benchmark consists of 29 different tasks ranging over different types such as document classification, sequence tagging, sentence similarity, and question answering, on which we evaluate 10 different German-pretrained models, thereby charting the landscape of German LLMs. In our comprehensive evaluation we find that encoder models are a good choice for most tasks, but also that the largest encoder model does not necessarily perform best for all tasks. We make our benchmark suite and a leaderboard publically available at https://supergleber.professor-x.de and encourage the community to contribute new tasks and evaluate more models on it (https://github.com/LSX-UniWue/SuperGLEBer).

SuperGLEBer: German Language Understanding Evaluation Benchmark

We introduce BUST, a comprehensive benchmark designed to evaluate detectors of texts generated by instruction-tuned large language models (LLMs). Unlike previous benchmarks, our focus lies on evaluating the performance of detector systems, acknowledging the inevitable influence of the underlying tasks and different LLM generators. Our benchmark dataset consists of 25K texts from humans and 7 LLMs responding to instructions across 10 tasks from 3 diverse sources. Using the benchmark, we evaluated 5 detectors and found substantial performance variance across tasks. A meta-analysis of the dataset characteristics was conducted to guide the examination of detector performance. The dataset was analyzed using diverse metrics assessing linguistic features like fluency and coherence, readability scores, and writer attitudes, such as emotions, convincingness, and persuasiveness. Features impacting detector performance were investigated with surrogate models, revealing emotional content in texts enhanced some detectors, yet the most effective detector demonstrated consistent performance, irrespective of writer’s attitudes and text styles. Our approach focused on investigating relationships between the detectors' performance and two key factors: text characteristics and LLM generators. We believe BUST will provide valuable insights into selecting detectors tailored to specific text styles and tasks and facilitate a more practical and in-depth investigation of detection systems for LLM-generated text.

BUST: Benchmark for the evaluation of detectors of LLM-Generated Text

Large Language Models (LLMs) are frequently used for multi-faceted language generation and evaluation tasks that involve satisfying intricate user constraints or taking into account multiple aspects and criteria. However, their performance can fall short, due to the model's lack of coherence and inability to plan and decompose the problem. We propose Branch-Solve-Merge (BSM), a Large Language Model program (Schlag et al., 2023) for tackling such challenging natural language tasks. It consists of branch, solve, and merge modules that are parameterized with specific prompts to the base LLM. These three modules plan a decomposition of the task into multiple parallel sub-tasks, independently solve them, and fuse the solutions to the sub-tasks. We apply our method to the tasks of LLM response evaluation and constrained text generation and evaluate its effectiveness with multiple LLMs, including Vicuna, LLaMA-2-chat, and GPT-4. BSM improves the evaluation correctness and consistency for each LLM by enhancing human-LLM agreement by up to 26%, reducing length and pairwise position biases by up to 50%, and allowing LLaMA-2-chat to match or outperform GPT-4 on most domains. On a constraint story generation task, BSM improves the coherence of stories while also improving constraint satisfaction by 12%.

Branch-Solve-Merge Improves Large Language Model Evaluation and Generation

Natural Language Generation (NLG) typically involves evaluating the generated text in various aspects (e.g., consistency and naturalness) to obtain a comprehensive assessment. However, multi-aspect evaluation remains challenging as it may require the evaluator to generalize to any given evaluation aspect even if it's absent during training. In this paper, we introduce X-Eval, a two-stage instruction tuning framework to evaluate text in both seen and unseen aspects customized by end users. X-Eval consists of two learning stages: the vanilla instruction tuning stage that improves the model's ability to follow evaluation instructions, and an enhanced instruction tuning stage that exploits the connections between fine-grained evaluation aspects to better assess text quality. To support the training of X-Eval, we collect AspectInstruct, the first instruction tuning dataset tailored for multi-aspect NLG evaluation spanning 27 diverse evaluation aspects with 65 tasks. To enhance task diversity, we devise an augmentation strategy that converts human rating annotations into diverse forms of NLG evaluation tasks, including scoring, comparison, ranking, and Boolean question answering. Extensive experiments across three essential categories of NLG tasks: dialogue generation, summarization, and data-to-text coupled with 21 aspects in meta-evaluation, demonstrate that X-Eval enables even a lightweight language model to achieve a comparable if not higher correlation with human judgments compared to the state-of-the-art NLG evaluators like GPT-4.

X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects

The development of highly fluent large language models (LLMs) has prompted increased interest in assessing their reasoning and problem-solving capabilities. We investigate whether several LLMs can solve a classic type of deductive reasoning problem from the cognitive science literature. The tested LLMs have limited abilities to solve these problems in their conventional form. We performed follow up experiments to investigate if changes to the presentation format and content improve model performance. We do find performance differences between conditions; however, they do not improve overall performance. Moreover, we find that performance interacts with presentation format and content in unexpected ways that differ from human performance. Overall, our results suggest that LLMs have unique reasoning biases that are only partially predicted from human reasoning performance and the human-generated language corpora that informs them.

Downloads

Next from NAACL 2024

Curated Datasets and Neural Models for Machine Translation of Informal Registers between Mayan and Spanish Vernaculars

Similar lecture

Iterative Prompt Refinement for Safer Text-to-Image Generation