Thailand

Phonology, the study of speech&#39;s structure and pronunciation rules, is a critical yet often overlooked component in Large Language Model (LLM) research. LLMs are widely used in various downstream applications that leverage phonology such as educational tools and poetry generation. Moreover, LLMs can potentially learn imperfect associations between orthographic and phonological forms from the training data. Thus, it is imperative to benchmark the phonological skills of LLMs. To this end, we present PhonologyBench, a novel benchmark consisting of three diagnostic tasks designed to explicitly test the phonological skills of LLMs in English: grapheme-to-phoneme conversion, syllable counting, and rhyme word generation. Despite having no access to speech data, LLMs showcased notable performance on the PhonologyBench tasks. However, we observe a significant gap of 17% and 45% on Rhyme Word Generation and Syllable counting, respectively, when compared to humans. Our findings underscore the importance of studying LLM performance on phonological tasks that inadvertently impact real-world applications. Furthermore, we encourage researchers to choose LLMs that perform well on the phonological task that is closely related to the downstream application since we find that no single model consistently outperforms the others on all the tasks.

ACL 2024

PhonologyBench: Evaluating Phonological Skills of Large Language Models

llms

phonology

large language models

evaluation

### 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**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Phonology, the study of speech's structure and pronunciation rules, is a critical yet often overlooked component in Large Language Model (LLM) research. LLMs are widely used in various downstream applications that leverage phonology such as educational tools and poetry generation. Moreover, LLMs can potentially learn imperfect associations between orthographic and phonological forms from the training data. Thus, it is imperative to benchmark the phonological skills of LLMs. To this end, we present PhonologyBench, a novel benchmark consisting of three diagnostic tasks designed to explicitly test the phonological skills of LLMs in English: grapheme-to-phoneme conversion, syllable counting, and rhyme word generation. Despite having no access to speech data, LLMs showcased notable performance on the PhonologyBench tasks. However, we observe a significant gap of 17% and 45% on Rhyme Word Generation and Syllable counting, respectively, when compared to humans. Our findings underscore the importance of studying LLM performance on phonological tasks that inadvertently impact real-world applications. Furthermore, we encourage researchers to choose LLMs that perform well on the phonological task that is closely related to the downstream application since we find that no single model consistently outperforms the others on all the tasks.

workshop paper

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

Recent work shows that large language models (LLMs) can answer multiple-choice questions using only the choices, but does this mean that MCQA leaderboard rankings of LLMs are largely influenced by abilities in choices-only settings? To answer this, we use a contrast set that probes if LLMs over-rely on choices-only shortcuts in MCQA. While previous works build contrast sets via expensive human annotations or model-generated data which can be biased, we employ graph mining to extract contrast sets from existing MCQA datasets. We use our method on UnifiedQA, a group of six commonsense reasoning datasets with high choices-only accuracy, to build an 820-question contrast set. After validating our contrast set, we test 12 LLMs, finding that these models do not exhibit reliance on choice-only shortcuts when given both the question and choices. Thus, despite the susceptibility of MCQA to high choices-only accuracy, we argue that LLMs are not obtaining high ranks on MCQA leaderboards solely due to their ability to exploit choices-only shortcuts.

Is Your Large Language Model Knowledgeable or a Choices-Only Cheater?

Large Language Models (LLMs) have revolutionized text generation across diverse domains, showcasing an ability to mimic human-like text with remarkable accuracy. Yet, these models frequently encounter a significant hurdle: producing hallucinations, a flaw particularly detrimental in the healthcare domain where precision is crucial. In this paper, we introduce ClinicalRAG, a novel multi-agent pipeline to rectify this issue by incorporating heterogeneous medical knowledge—both structured and unstructured—into LLMs to bolster diagnosis accuracy. ClinicalRAG can extract related medical entities from user inputs and dynamically integrate relevant medical knowledge during the text generation process. Comparative analyses reveal that ClinicalRAG significantly outperforms knowledge-deficient methods, offering enhanced reliability in clinical decision support. This advancement marks a pivotal proof-of-concept step towards mitigating misinformation risks in healthcare applications of LLMs.

ClinicalRAG: Enhancing Clinical Decision Support through Heterogeneous Knowledge Retrieval

Relation extraction aims to classify the relationships between two entities into pre-defined categories. While previous research has mainly focused on sentence-level relation extraction, recent studies have expanded the scope to document-level relation extraction. Traditional relation extraction methods heavily rely on human-annotated training data, which is time-consuming and labor-intensive. To mitigate the need for manual annotation, recent weakly-supervised approaches have been developed for sentence-level relation extraction while limited work has been done on document-level relation extraction. Weakly-supervised document-level relation extraction faces significant challenges due to an imbalanced number “no relation” instances and the failure of directly probing pretrained large language models for document relation extraction. To address these challenges, we propose PromptRE, a novel weakly-supervised document-level relation extraction method that combines prompting-based techniques with data programming. Furthermore, PromptRE incorporates the label distribution and entity types as prior knowledge to improve the performance. By leveraging the strengths of both prompting and data programming, PromptRE achieves improved performance in relation classification and effectively handles the “no relation” problem. Experimental results on ReDocRED, a benchmark dataset for document-level relation extraction, demonstrate the superiority of PromptRE over baseline approaches.

PromptRE: Weakly-Supervised Document-Level Relation Extraction via Prompting-Based Data Programming

Recent surge in the accessibility of large language models (LLMs) to the general population can lead to untrackable use of such models for medical-related recommendations. Language generation via LLMs models has two key problems: firstly, they are prone to hallucination and therefore, for any medical purpose they require scientific and factual grounding; secondly, LLMs pose tremendous challenge to computational resources due to their gigantic model size. In this work, we introduce pRAGe, a Pipeline for Retrieval Augmented Generation and Evaluation of medical paraphrases generation using Small Language Models (SLM). We study the effectiveness of SLMs and the impact of external knowledge base for medical paraphrase generation in French.

Retrieve, Generate, Evaluate: A Case Study for Medical Paraphrases Generation with Small Language Models

Recent research shows that more data and larger models can provide more accurate solutions to natural language problems that require reasoning. However, models can easily fail to provide solutions in unobserved levels of compositional complexity because they might not obtain the level of abstraction needed for generalizability. To alleviate this issue, we propose to train the models with neuro-symbolic techniques that can exploit the logical rules of reasoning as constraints and provide additional supervision sources to the model. Training models to adhere to the regulations of reasoning pushes them to make more effective abstractions needed for generalizability and transfer learning. We focus on a challenging problem of spatial reasoning over text, and our results on multiple benchmarks confirm our hypothesis of effective domain transfer based on neuro-symbolic training. We utilize our symbolic training approach on multiple commonly used language models.

Tuning Language Models with Spatial Logic for Complex Reasoning

We constructed a database of Japanese expressions based on route information. Using 20 maps as stimuli, we requested descriptions of routes between two points on each map from 40 individuals per route, collecting 1600 route information reference expressions. We determined whether the expressions were based solely on relative reference expressions by using landmarks on the maps. In cases in which only relative reference expressions were used, we labeled the presence or absence of information regarding the starting point, waypoints, and destination. Additionally, we collected clarity ratings for each expression using a survey.

Collection of Japanese Route Information Reference Expressions Using Maps as Stimuli

Top-view perspective denotes a typical way in which humans read and reason over different types of maps, and it is vital for localization and navigation of humans as well as of 'non-human' agents, such as the ones backed by large Vision-Language Models (VLMs). Nonetheless, spatial reasoning capabilities of modern VLMs remain unattested and underexplored. In this work, we thus study their capability to understand and reason over spatial relations from the top view. The focus on top view also enables controlled evaluations at different granularity of spatial reasoning; we clearly disentangle different abilities (e.g., recognizing particular objects versus understanding their relative positions). We introduce the TopViewRS (Top-View Reasoning in Space) dataset, consisting of 11,384 multiple-choice questions with either realistic or semantic top-view map as visual input. We then use it to study and evaluate VLMs across 4 perception and reasoning tasks with different levels of complexity. Evaluation of 10 representative open- and closed-source VLMs reveals the gap of more than 50% compared to average human performance, and it is even lower than the random baseline in some cases. Although additional experiments show that Chain-of-Thought reasoning can boost model capabilities by 5.82% on average, the overall performance of VLMs remains limited. Our findings underscore the critical need for enhanced model capability in top-view spatial reasoning and set a foundation for further research towards human-level proficiency of VLMs in real-world multimodal tasks.

TopViewRS: Vision-Language Models as Top-View Spatial Reasoners

This paper introduces the concept of Language-Guided World Models (LWMs) -- probabilistic models that can simulate environments by reading texts. Agents equipped with these models provide humans with more extensive and efficient control, allowing them to simultaneously alter agent behaviors in multiple tasks via natural verbal communication. In this work, we take initial steps in developing robust LWMs that can generalize to compositionally novel language descriptions. We design a challenging world modeling benchmark based on the game of MESSENGER (Hanjie et al., 2021), featuring evaluation settings that require varying degrees of compositional generalization. Our experiments reveal the lack of generalizability of the state-of-the-art Transformer model, as it offers marginal improvements in simulation quality over a no-text baseline. We devise a more robust model by fusing the Transformer with the EMMA attention mechanism (Hanjie et al., 2021). Our model substantially outperforms the Transformer and approaches the performance of a model with an oracle semantic parsing and grounding capability. To demonstrate the practicality of this model in improving AI safety and transparency, we simulate a scenario in which the model enables an agent to present plans to a human before execution, and to revise plans based on their language feedback.

Language-guided World Models: A Model-based Approach to AI Control

In this work, we evaluate the adaptability of neural agents towards assumed partner behaviors in a collaborative reference game. In this game, success is achieved when a knowledgeable guide can verbally lead a follower to the selection of a specific puzzle piece among several distractors. We frame this language grounding and coordination task as a reinforcement learning problem and measure to which extent a common reinforcement training algorithm (PPO) is able to produce neural agents (the guides) that perform well with various heuristic follower behaviors that vary along the dimensions of confidence and autonomy. We experiment with a learning signal that in addition to the goal condition also respects an assumed communicative effort. Our results indicate that this novel ingredient leads to communicative strategies that are less verbose (staying silent in some of the steps) and that with respect to that the guide’s strategies indeed adapt to the partner’s level of confidence and autonomy.

Learning Communication Policies for Different Follower Behaviors in a Collaborative Reference Game

We create MTI(Multi-Task Inference)-Bench and test whether language models can solve complicated instructions, consisted of two or more instructions, at once.

Downloads

Next from ACL 2024

Is Your Large Language Model Knowledgeable or a Choices-Only Cheater?

Similar lecture

P-CoT: A Pedagogically-motivated Participatory Chain-of-Thought Prompting for Phonological Reasoning in LLMs

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL 2024

Is Your Large Language Model Knowledgeable or a Choices-Only Cheater?

Similar lecture

P-CoT: A Pedagogically-motivated Participatory Chain-of-Thought Prompting for Phonological Reasoning in LLMs

Downloads