United States

Pronunciation feedback in language learning depends on accurate detection of learner errors, but it is unclear whether modern ASR systems are suitable for this purpose. Their language models recover intended words rather than what was actually pronounced, systematically masking mispronunciations. This is a tendency we call \emph{intent bias}. By evaluating eight ASR systems spanning three architectures on two L2 English corpora, we find that overcorrection rate correlates inversely with word error rate. In other words, ASR systems with lower WER tend to mask more pronunciation errors. We propose surface-faithful reranking, an inference-time method that uses phoneme-level acoustic similarity to select N-best hypotheses closer to what the learner actually said. Without retraining or access to model internals, the method reduces the false acceptance rate of mispronunciations by 6.0 percentage points on L2-ARCTIC and 4.8 on Speechocean762. The improvement is consistent across age groups and first-language backgrounds, though substantial overcorrection remains, pointing to the need for pronunciation-aware ASR objectives.

ACL 2026

Intent vs. Surface: Recovering Acoustic Realization from Modern ASR for Pronunciation Training

mispronunciation detection

capt

automatic speech recognition

## 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.

workshop paper

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields 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.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>

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 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

Registration Required

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

Research in AI applied to education increasingly relies on large-scale, high-quality datasets to support the development and evaluation of learning analytics and intelligent educational systems. Open educational resources provide a promising foundation, yet few datasets integrate structured instructional content with assessment materials in a multimodal form. In this study, we introduce a large-scale multimodal educational dataset (EduMUSE - \underline{Educ}ational \underline{M}ultimodal \underline{U}nderstanding \& \underline{S}olution Datas\underline{e}t) constructed from OpenStax undergraduate textbooks across multiple domains. The dataset integrates hierarchically structured instructional text, figures, exercises, and, when available, official solutions. For exercises with solutions, we introduce an automatic method that associates each exercise with a focused instructional subsection rather than entire textbook chapters, estimating subsection relevance via solution likelihood under candidate contexts using a vision–language model. We analyze the impact of contextualization on the behavior of vision–language models across different contexts. Results indicate that subsection-level instructional context has a measurable impact on model performance, with variation across model scales and task formulations. The dataset and code are released as open source at \url{https://anonymous.4open.science/r/EduMUSE-1EF8/} to support reproducible research in multimodal educational modeling and to facilitate generating similar datasets using our approach.

EduMUSE: A Multimodal Educational Dataset with Automatically Extracted Instructional Context

Automated short answer scoring (ASAS) is shifting from discriminative, fine-tuned models to large language models (LLMs) used in few-shot settings. This paradigm leverages LLMs' broad world knowledge and ease of deployment, but limited task-specific data may reduce alignment on complex scoring tasks. In particular, its impact on scoring partially correct responses that require nuanced interpretation remains underexplored.
We investigate the relationship between the degree of task-specific adaptation of different models and quality-conditioned scoring agreement. We compare three LLMs (GPT-5.2, GPT-4o, Claude Opus 4.5) in few-shot mode, a fine-tuned BERT-based encoder, and a human expert on two open-ended biology items, using several hundred student responses and ground truth scores provided by a biology education expert.
The results show that human–human agreement is highest and stable across the full quality spectrum. All AI models perform well on fully correct and fully incorrect responses, but exhibit substantial degradation on mid-range responses. This mid-range degradation is conditioned on task-specific adaptation: It is most severe in few-shot LLMs with few examples and decreases as task-specific data increases, with fine-tuned encoder models performing best.
This mid-range degradation may lead to inequitable evaluation of responses produced by students with developing understanding. Our findings highlight the importance of quality-conditioned fairness, with particular attention to mid-range responses.

Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation

Various aspects of the Elicited Imitation Test (EIT), a sentence repetition task for language assessment, can be automated, for example in terms of test administration or automatic scoring. It is potentially also possible to generate test items with Large Language Models (LLMs). This study investigates the potential of GPT-4o for item creation in the context of EIT, creating a parallel form to two popular and validated tests. We analysed the tests in terms of their linguistic and psychometric properties. While the items created by the LLM show some difference in grammatical structures when compared to human-written items, linguistic complexity results did not differ significantly between tests. Psychometric properties showed only minor differences. These findings lend support to the potential of Automatic Item Generation with LLMs in the context of sentence repetition tasks and might support the process of standardisation in SLA research and testing by enabling parallel test creation.

Using LLMs for item creation: Validating the potential of automatically generated sentence repetition test items for language assessment

Young athletes, parents and coaches are increasingly encountering training metrics derived from wearable technology, yet such metrics rarely provide sufficient information on their own. We present a rule-based data-to-text framework designed to promote data literacy in youth football, generating concise, stakeholder-specific summaries of training sessions. A rule layer maps duration-normalised indicators to structured facts about the session profile, internal intensity, speed exposure and movement dynamics. A large language model then verbalises these facts for coaches, parents or players. We compare direct generation from raw metrics, strictly rule-based generation and an extended RULES+CONTEXT implementation that combines validated facts with raw metrics and explicit threshold definitions. In the open-weight setting examined here, the selected models are also adapted using LoRA. When evaluated on 122 player-session records from a U15 environment, it was found that rule grounding improved reliability and audience adaptation compared to direct generation. A school-based expert evaluation also provided preliminary evidence that player-facing explanations in the extended setting can remain accurate, comprehensible, and useful in practice.

From Metrics to Meaning: Rule-Grounded LLM Explanations for Data Literacy in Youth Football

Productive struggle is a critical component of mathematics education, requiring students to actively work through ideas rather than just making errors. However, identifying this struggle from text transcripts is challenging because students often mask confusion with epistemic hedging rather than direct statements. Zero-shot large language models exhibit a conservative bias, systematically under-detecting struggle in classroom discourse. We introduce a two-stage NLP pipeline comprising a lexical heuristic gate and an LLM subtype classifier. Our model achieves 90.0% binary accuracy and 84.0% 4-category accuracy. We demonstrate the pedagogical value of this tool by showing that struggle is uniquely concentrated during explicit mathematical reasoning, offering educators a scalable method for root-cause analysis.

Classification of Student Struggle in Mathematics

Recent advances in the capabilities of conversational agents based on large language models make them a very promising tool for role playing K-12 students in order to train educators in conversational teaching practices, such as eliciting student thinking, explaining disciplinary content, and facilitating a classroom discussion. In fact, such simulations can and have been developed relatively quickly and without data to machine-learn from -- neither classroom data nor human-simulated data. To enhance the usefulness and effectiveness of such teaching simulations, it is necessary to provide pedagogically sound, timely, and personalized feedback to the educator about their simulation performance. In this study, we present experiments on fine-tuning models to evaluate educator performance in an elicitation teaching simulation. The models are developed with data collected during usability testing of the simulation and evaluated on real user data. We show that even with relatively little fine-tuning data, robust performance can be obtained

Data-lean fine-tuning of models for evaluating teacher performance in a GenAI-led elicitation simulation

Recent advances in large language models (LLMs) have led to the development of AI-powered tutoring systems that provide interactive support via dialogue. To enable these tutoring systems to provide personalized support, it is essential to assess student performance at each turn, motivating knowledge tracing (KT) in dialogue settings. However, existing dialogue-based KT approaches often ignore question difficulty modeling and rely on opaque latent representations from LLMs, hindering accurate and interpretable prediction. In this work, we propose an interpretable difficulty-aware conversational KT framework built upon LLMs, which explicitly models students' abilities and the tutor-posed tasks at each turn. The framework incorporates the original textual question and the next tutor-posed task to estimate the student's knowledge state and the difficulty of the upcoming turn. Furthermore, it integrates Item Response Theory to map LLM's outputs into student ability and question difficulty parameters, enabling interpretable prediction of student performance grounded in cognitive theories of learning. We evaluate the framework on two tutor-student dialogue datasets. Both quantitative and qualitative results show that our framework outperforms existing KT baselines, meanwhile generating interpretable outputs consistent with cognitive theory.

Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues

Rubrics are the primary reference for manual scoring of constructed responses, and there is growing interest in their use in automated scoring methodologies. In this work, we propose Aspect-Grounded Rubric–Answer Alignment (AGRAA), a rubric-based end-to-end scoring framework that models rubric descriptors as latent aspect spaces. Concretely, rubric descriptors are represented as low-dimensional subspaces derived from contextualised transformer embeddings, and student responses are scored according to how strongly their representations align with these rubric-induced spaces relative to the residual space outside them. This formulation provides a geometrically grounded interpretation of rubric-based scoring while enabling end-to-end training with standard transformer encoders. We introduce three distinct architectural variants and evaluate them on multiple short-answer and essay scoring datasets. Across these tasks, AGRAA achieves predictive performance highly competitive with strong neural and feature-based baselines. In addition, the framework yields interpretable intermediate representations that expose which rubric-defined aspects contribute to scoring decisions, enabling decision-aligned explanations grounded in rubric descriptors.

Rubrics as Semantic Subspaces: A Unified Approach to Rubric-based Constructed Response Scoring across Short Answers and Essays

This paper proposes a computational framework to operationalize optimal challenge based on Krashen's Input Hypothesis for open-ended conversational English as a Foreign Language (EFL) tutoring. Because conversational EFL tutoring relies on dynamically generated exercises rather than static item banks, traditional difficulty estimation methods cannot verify if a task is appropriately calibrated to a learner. Rather than treating difficulty as an intrinsic item property, we measure it directly from real-time interactional behavior, classifying exercises into three alignment states: Under-Challenged, Optimally Challenged, and Over-Challenged. Using 1,566 exercises from the Teacher-Student Chatroom Corpus, we first demonstrate that a learner's history of these states highly predicts their success on subsequent tasks. We then leverage this micro-level predictive model to construct an in-situ learning gain proxy, tracking shifts in a student's expected success probability across a session. Analyzing these macro-level trajectories, we find that sessions with higher proportions of over-challenging exercises systematically yield lower estimated gains. Crucially, increasing the proportion of optimally challenging interactions drives statistically significantly greater capability improvement than providing under-challenging tasks, providing quantitative evidence consistent with the Input Hypothesis in open-ended tutoring.

Measuring Optimal Challenge: Trajectory-Based Difficulty Alignment in Open-Ended Language Tutoring

Investigating the degree to which large language models (LLMs) affect teaching and learning in universities can help identify strategies for integrating LLMs in a way that supports, rather than undermines, student learning outcomes. This study examined how varying levels of LLM assistance affect writing performance, engagement, and perceived authorship. We report a pilot study in which 24 college students were randomly assigned to write a short essay with no LLM access, limited access (<=3 prompts, responses capped at 100 words), or unlimited access. Overall essay quality was statistically indistinguishable across groups. Yet writing behavior and perceived authorship diverged sharply: students with limited access reported higher ownership (62.5% would submit the essay as independent work, vs. 25% in the unlimited group), stronger organizational gains, and more strategic, revision-focused prompting. The unlimited group spent more time writing, produced essays more similar to LLM output, and reported reduced creative expression. Our findings suggest that constraining, rather than banning, LLM access may preserve authorship confidence while retaining the scaffolding benefits of AI assistance.

Downloads

Next from ACL 2026

EduMUSE: A Multimodal Educational Dataset with Automatically Extracted Instructional Context

Similar lecture

ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction