Mexico

Large language models (LLMs) have emerged as valuable tools for many natural language understanding tasks. In safety-critical applications such as healthcare, the utility of these models is governed by their ability to generate factually accurate and complete outputs. In this work, we present dialog-enabled resolving agents (DERA). DERA is a paradigm made possible by the increased conversational abilities of LLMs. It provides a simple, interpretable forum for models to communicate feedback and iteratively improve output. We frame our dialog as a discussion between two agent types -- a Researcher, who processes information and identifies crucial problem components, and a Decider, who has the autonomy to integrate the Researcher&#39;s information and makes judgments on the final output.

We test DERA against three clinically-focused tasks, with GPT-4 serving as our LLM. DERA shows significant improvement over the base GPT-4 performance in both human expert preference evaluations and quantitative metrics for medical conversation summarization and care plan generation. In a new finding, we also show that GPT-4&#39;s performance (70%) on an open-ended version of the MedQA question-answering (QA) dataset (Jin 2021; USMLE) is well above the passing level (60%), with DERA showing similar performance. We will release the open-ended MedQA dataset.

NAACL 2024

DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents

large language models; safety; dialogue; summarization

Large language models (LLMs) have emerged as valuable tools for many natural language understanding tasks. In safety-critical applications such as healthcare, the utility of these models is governed by their ability to generate factually accurate and complete outputs. In this work, we present dialog-enabled resolving agents (DERA). DERA is a paradigm made possible by the increased conversational abilities of LLMs. It provides a simple, interpretable forum for models to communicate feedback and iteratively improve output. We frame our dialog as a discussion between two agent types -- a Researcher, who processes information and identifies crucial problem components, and a Decider, who has the autonomy to integrate the Researcher's information and makes judgments on the final output.

We test DERA against three clinically-focused tasks, with GPT-4 serving as our LLM. DERA shows significant improvement over the base GPT-4 performance in both human expert preference evaluations and quantitative metrics for medical conversation summarization and care plan generation. In a new finding, we also show that GPT-4's performance (70%) on an open-ended version of the MedQA question-answering (QA) dataset (Jin 2021; USMLE) is well above the passing level (60%), with DERA showing similar performance. We will release the open-ended MedQA dataset.

workshop paper

## 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

Text generation opens up new prospects for overcoming the lack of open corpora in fields such as healthcare, where data sharing is bound by confidentiality. In this study, we compare the performance of encoder-decoder and decoder-only language models for the controlled generation of clinical cases in French. To do so, we fine-tuned several pre-trained models on French clinical cases for each architecture and generate clinical cases conditioned by patient demographic information (gender and age) and clinical features.
Our results suggest that encoder-decoder models are easier to control than decoder-only models, but more costly to train.

Using Structured Health Information for Controlled Generation of Clinical Cases in French

Biomedical Entity Linking (BEL) is a challenging task for low-resource languages, due to the lack of appropriate resources: datasets, knowledge bases (KBs), and pre-trained models. In this paper, we propose an approach to create a biomedical knowledge base for German BEL using UMLS information from Wikidata, that provides good coverage and can be easily extended to further languages. As a further contribution, we adapt several existing approaches for use in the German BEL setup, and report on their results. The chosen methods include a sparse model using character n-grams, a multilingual biomedical entity linker, and two general-purpose text retrieval models. Our results show that a language-specific KB that provides good coverage leads to most improvement in entity linking performance, irrespective of the used model. The finetuned German BEL model, newly created UMLS$_{Wikidata}$ KB as well as the code to reproduce our results are publicly available.

Leveraging Wikidata for Biomedical Entity Linking in a Low-Resource Setting: A Case Study for German

Clinical Decision Support Systems assist medical professionals in providing optimal care for patients.
A prominent data source used for creating tasks for such systems is the Medical Information Mart for Intensive Care (MIMIC).
MIMIC contains electronic health records (EHR) gathered in a tertiary hospital in the United States.
The majority of past work is based on the third version of MIMIC, although the fourth is the most recent version.
This new version, not only introduces more data into MIMIC, but also increases the variety of patients.
While MIMIC-III is limited to intensive care units, MIMIC-IV also offers EHRs from the emergency department.
In this work, we investigate how to adapt previous work to update clinical outcome prediction for MIMIC-IV.
We revisit several established tasks, including prediction of diagnoses, procedures, length-of-stay, and also introduce a novel task: patient routing prediction.
Furthermore, we quantitatively and qualitatively evaluate all tasks on several bio-medical transformer encoder models.
Finally, we provide narratives for future research directions in the clinical outcome prediction domain.
We make our source code publicly available to reproduce our experiments, data, and tasks.

Revisiting Clinical Outcome Prediction for MIMIC-IV

We explore the potential of Large Language Models (LLMs) to assist and potentially correct physicians in medical decision-making tasks. We evaluate several LLMs, including Meditron, Llama2, and Mistral, to analyze the ability of these models to interact effectively with physicians across different scenarios. We consider questions from PubMedQA and several tasks, ranging from binary (yes/no) responses to long answer generation, where the answer of the model is produced after an interaction with a physician. Our findings suggest that prompt design significantly influences the downstream accuracy of LLMs and that LLMs can provide valuable feedback to physicians, challenging incorrect diagnoses and contributing to more accurate decision-making. For example, when the physician is accurate 38% of the time, Mistral can produce the correct answer, improving accuracy up to 74% depending on the prompt being used, while Llama2 and Meditron models exhibit greater sensitivity to prompt choice. Our analysis also uncovers the challenges of ensuring that LLM-generated suggestions are pertinent and useful, emphasizing the need for further research in this area.

Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain

We explore the utility of pre-trained Large Language Models (LLMs) in detecting the presence, subtypes, and severity of aphasia across English and Mandarin Chinese speakers. Our investigation suggests that even without fine-tuning or domain-specific training, pre-trained LLMs can offer some insights on language disorders, regardless of speakers' first language. Our analysis also reveals noticeable differences between English and Chinese LLMs. While the English LLMs exhibit near-chance level accuracy in subtyping aphasia, the Chinese counterparts demonstrate less than satisfactory performance in distinguishing between individuals with and without aphasia. This research advocates for the importance of linguistically tailored and specified approaches in leveraging LLMs for clinical applications, especially in the context of multilingual populations.

Leveraging pre-trained large language models for aphasia detection in English and Chinese speakers

Leveraging large language models (LLMs) as evaluators are becoming a popular trend to replace costly human evaluations. Despite evident benefits, we raise concerns on the reliability of LLM evaluators especially within the context of consistency. We perform extensive assessments on diverse setups of consistency of LLM evaluators and propose methods to improve consistency without the loss of accuracy.

ConsEval: Illuminating and Improving the Consistency of LLM Evaluators

In order to build reliable and trustworthy NLP applications, models need to be both fair across different demographics and explainable. Usually these two objectives, fairness and explainability, are optimized and/or examined independently of each other. Instead, we argue that forthcoming, trustworthy NLP systems should consider both.
In this work, we perform a first study to understand how they influence each other: do fair(er) models rely on more plausible explanations? and vice versa. To this end, we conduct experiments on two English multi-class text classification datasets, BIOS and ECtHR, that provide information on gender and nationality, respectively, as well as human-annotated rationales. 
We fine-tune pre-trained language models with several methods for (i) bias mitigation, which aims to improve fairness; (ii) rationale extraction, which aims to produce plausible explanations.
We find that bias mitigation algorithms do not always lead to fairer models. Moreover, in our analysis, we see that empirical fairness and explainability are orthogonal.

On the Interplay between Fairness and Explainability

Dominant pre-trained language models (PLMs) have been successful in high-quality natural language generation.
However, the analysis of their generation is not mature: do they acquire generalizable linguistic abstractions, or do they simply memorize and recover substrings of the training data?
Especially, few studies focus on domain-specific PLM.
In this study, we pre-trained domain-specific GPT-2 models using a limited corpus of Japanese newspaper articles and quantified memorization of training data by comparing them with general Japanese GPT-2 models.
Our experiments revealed that domain-specific PLMs sometimes "copy and paste" on a large scale.
Furthermore, we replicated the empirical finding that memorization is related to duplication, model size, and prompt length, in Japanese the same as in previous English studies.
Our evaluations are relieved from data contamination concerns by focusing on newspaper paywalls, which prevent their use as training data.
We hope that our paper encourages a sound discussion such as the security and copyright of PLMs.

Quantifying Memorization of Domain-Specific Pre-trained Language Models using Japanese Newspaper and Paywalls

Large Language Models (LLMs) have been widely used in real-world applications. However, as LLMs evolve and new datasets are released, it becomes crucial to build processes to evaluate and control the models' performance. In this paper, we describe how to add Robustness, Accuracy, and Toxicity scores to model comparison tables, or leaderboards. We discuss the evaluation metrics, the approaches considered, and present the results of the first evaluation round for model Robustness, Accuracy, and Toxicity scores. Our results show that GPT 4 achieves top performance on robustness and accuracy test, while Llama 2 achieves top performance on the toxicity test. We note that newer open-source models such as open chat 3.5 and neural chat 7B can perform well on these three test categories. Finally, domain-specific tests and models are also planned to be added to the leaderboard to allow for a more detailed evaluation of models in specific areas such as healthcare, legal, and finance.

Holistic Evaluation of Large Language Models: Assessing Robustness, Accuracy, and Toxicity for Real-World Applications

With the widespread adoption of large language models (LLMs) in numerous applications, the challenge of factuality and the propensity for hallucinations has emerged as a significant concern. To address this issue, particularly in retrieval-augmented in-context learning, we introduce the hierarchical graph of thoughts (HGOT), a structured, multi-layered graph approach designed to enhance the retrieval of pertinent passages during in-context learning. The framework utilizes the emergent planning capabilities of LLMs, employing the divide-and-conquer strategy to break down complex queries into manageable sub-queries. It refines self-consistency majority voting for answer selection, which incorporates the recently proposed citation recall and precision metrics to assess the quality of thoughts, linking an answer's credibility intrinsically to the thought's quality. This methodology introduces a weighted system in majority voting, prioritizing answers based on the citation quality of their thoughts. Additionally, we propose a scoring mechanism for evaluating retrieved passages, considering factors such as citation frequency and quality, self-consistency confidence, and the retrieval module's ranking. Experiments indicate that HGOT excels as a versatile approach, outperforming competing models in FEVER by up to 7% and matching leading models such as Retrieve-then-Read in Open-SQuAD, and DSP in HotPotQA, demonstrating its efficacy in enhancing LLMs' factuality.

DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents

Downloads

Next from NAACL 2024

Using Structured Health Information for Controlled Generation of Clinical Cases in French

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES