Mexico

Language models (LMs) encode world knowledge in their internal parameters through training. However, LMs may learn personal and confidential information from the training data, leading to privacy concerns such as data leakage. Therefore, research on knowledge deletion from LMs is essential. This study focuses on the knowledge stored in LMs and analyzes the relationship between the side effects of knowledge deletion and the entities related to the knowledge. Our findings reveal that deleting knowledge related to popular entities can have catastrophic side effects. Furthermore, this research is the first to analyze knowledge deletion in models trained on synthetic knowledge graphs, indicating a new direction for controlled experiments.

NAACL 2024

The Curse of Popularity: Popular Entities have Catastrophic Side Effects when Deleting Knowledge from Language Models

knowledge deletion

knowledge editing

knowledge graph

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

With the remarkable development of large language models (LLMs), ensuring the factuality of output has become a challenge.
However, having all the contents of the response with given knowledge or facts is not necessarily a good thing in dialogues.
This study aimed to achieve both attractiveness and factuality in a dialogue response for which a task was set to predict sentences that do not require factual correctness judgment such as agreeing, or personal opinions/feelings.
We created a dataset, dialogue dataset annotated with fact-check-needed label (DDFC), for this task via crowdsourcing, and classification tasks were performed on several models using this dataset.
The model with the highest classification accuracy could yield about $88$\% accurate classification results.

Detecting Response Generation Not Requiring Factual Judgment

The ability to generate code using large language models (LLMs) has been increasing year by year. However, studies on code generation at the repository level are not very active. In repository-level code generation, it is necessary to refer to related code snippets among multiple files. By taking the similarity between code snippets, related files are searched and input into an LLM, and generation is performed. This paper proposes a method to search for related files (code search) by taking similarities not between code snippets but between the texts converted from the code snippets by the LLM. We confirmed that converting to text improves the accuracy of code search.

Improving Repository-level Code Search with Text Conversion

Few-shot learning techniques for Event Extraction are developed to alleviate the cost of data annotation. However, most studies on few-shot event extraction only focus on event trigger detection and no study has been proposed on argument extraction in a meta-learning context. In this paper, we investigate few-shot event argument extraction using prototypical networks, casting the task as a relation classification problem. Furthermore, we propose to enhance the relation embeddings by injecting syntactic knowledge into the model using graph convolutional networks. Our experimental results show that our proposed approach achieves strong performance on ACE 2005 in several few-shot configurations, and highlight the importance of syntactic knowledge for this task. More generally, our paper provides a unified evaluation framework for meta-learning approaches for argument extraction.

Few-Shot Event Argument Extraction Based on a Meta-Learning Approach

The development of large language models (LLMs) is becoming increasingly significant, and there is a demand for high-quality, large-scale corpora for their pretraining.
The quality of a web corpus is especially essential to improve the performance of LLMs because it accounts for a large proportion of the whole corpus. However, filtering methods for Web corpora have yet to be established.
In this paper, we present empirical studies to reveal which filtering methods are indeed effective and analyze why they are.
We build classifiers and language models in Japanese that can process large amounts of corpora rapidly enough for pretraining LLMs in limited computational resources. By evaluating these filtering methods based on a Web corpus quality evaluation benchmark, we reveal that the most accurate method is the N-gram language model. Indeed, we empirically present that strong filtering methods can rather lead to lesser performance in downstream tasks.
We also report that the proportion of some specific topics in the processed documents decreases significantly during the filtering process.

Investigating Web Corpus Filtering Methods for Language Model Development in Japanese

The fill-in-the-blank prompts are widely used to evaluate how well pre-trained language models (PLMs) capture real-world factual knowledge. 
However, the prompt-based evaluation results vary significantly depending on the linguistic expressions of the prompts, even for the same knowledge. 
To evaluate the ability of PLMs to understand facts more fairly and from diverse perspectives, we propose a new factual knowledge probing dataset - MyriadLAMA, and the evaluation benchmark, BELIEF. 
MyriadLAMA is a fill-in-the-blank dataset that contains numerous lexically, syntactically, and semantically diverse prompts for each fact. 
BELIEF is a method to mitigate prompt bias in evaluating knowledge in PLMs by aggregating results from multiple prompts for each fact.
Based on MyriadLAMA, BELIEF enables the comprehensive evaluation of factual knowledge in PLMs from multiple perspectives, covering the perspective of consistency and reliability.
Our experiments confirm the effectiveness of BELIEF via the evaluation of factual knowledge across multiple PLMs such as BERT.

BELIEF: A Bias-free Estimation of Language Models in Factual Knowledge Understanding

We explore Visual Prompt Injection (VPI) that maliciously exploits the ability of Large Vision-Language Models (LVLMs) to follow instructions drawn onto the input image.
We propose a new VPI method, Goal Hijacking via Visual Prompt Injection (GHVPI), that swaps the execution task of LVLMs from an original task to an alternative task designated by an attacker.
The quantitative analysis indicates that GPT-4V is vulnerable to GHVPI and demonstrates a notable attack success rate of 15.8%, which is a significant security risk.
Our analysis also shows that successful GHVPI requires high character recognition capability and instruction-following ability in LVLMs.

Empirical Analysis of Large Vision Language Models against Goal Hijacking via Visual Prompt Injection

Non-autoregressive (NAR) language models are known for their low latency in neural machine translation (NMT). However, a performance gap exists between NAR and autoregressive models due to the large decoding space and difficulty in capturing dependency between target words accurately. Compounding this, preparing appropriate training data for NAR models is a non-trivial task, often exacerbating exposure bias. To address these challenges, we apply reinforcement learning (RL) to Levenshtein Transformer, a representative edit-based NAR model, demonstrating that RL with self-generated data can enhance the performance of edit-based NAR models. We explore two RL approaches: stepwise reward maximization and episodic reward maximization. We discuss the respective pros and cons of these two approaches and empirically verify them. Moreover, we experimentally investigate the impact of temperature setting on performance, confirming the importance of proper temperature setting for NAR models' training.

Reinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translation

In-context Learning (ICL) is the ability of Large Language Models (LLMs) to perform new tasks when conditioned on prompts comprising a few task examples. However, ICL performance can be critically sensitive to the choice of examples. To dynamically select the best examples for every test input, we propose Example Gisting, a novel approach for training example encoders through supervised fine-tuning with an attention bottleneck between the inputs and outputs. These gist models form the basis for GistScore, a novel metric for scoring and selecting informative examples. Further, in addition to fine-tuning gist models on each dataset, we also experiment with training a single model on a large multi-task corpus that can then be used for new tasks out-of-the-box, ensuring a training-free ICL pipeline. Evaluations with 21 datasets spanning 9 tasks and 8 diverse LLMs show that our fine-tuned models yield state-of-the-art ICL performance with over 20% absolute gain over off-the-shelf retrievers and 5% over the best prior methods. Further, our multi-task model generalizes to new tasks and datasets and is on par or better than all baselines while being three orders faster than the strongest training-free baseline.

GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks

To reduce the cost of training models for each language for developers of natural language processing applications, pre-trained multilingual sentence encoders are promising. However, since training corpora for such multilingual sentence encoders contain only a small amount of text in languages other than English, they suffer from performance degradation for non-English languages. To improve the performance of pre-trained multilingual sentence encoders for non-English languages, we propose a method of machine translating a source sentence into English and then inputting it together with the source sentence in a multi-source manner. Experimental results on sentiment analysis and topic classification tasks in Japanese revealed the effectiveness of the proposed method.

Multi-Source Text Classification for Multilingual Sentence Encoder with Machine Translation

In the pursuit of supporting more languages around the world, tools that characterize properties of languages play a key role in expanding the existing multilingual NLP research. In this study, we focus on a widely used typological knowledge base, URIEL, which aggregates linguistic information into numeric vectors. Specifically, we delve into the soundness and reproducibility of the approach taken by URIEL in quantifying language similarity. Our analysis reveals URIEL's ambiguity in calculating language distances and in handling missing values. Moreover, we find that URIEL does not provide any information about typological features for 31\% of the languages it represents, undermining the reliabilility of the database, particularly on low-resource languages. Our literature review suggests URIEL and lang2vec are used in papers on diverse NLP tasks, which motivates us to rigorously verify the database as the effectiveness of these works depends on the reliability of the information the tool provides.

The Curse of Popularity: Popular Entities have Catastrophic Side Effects when Deleting Knowledge from Language Models

Next from NAACL 2024

Detecting Response Generation Not Requiring Factual Judgment

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES