United States

Speech-based screening for mild cognitive impairment offers a highly accessible way to detect early cognitive decline. While most existing work focuses on English, cross-linguistic research is emerging to examine how cognitive decline manifests across languages. Studies on the Interspeech&#39;24 TAUKADIAL dataset, comprising English and Chinese speech recordings, consistently report higher classification performance on Chinese, yet the cause of this cross-lingual discrepancy remains unexplored. We examine this gap using Gemini 2.5 Pro, a multimodal large language model, using zero-shot and in-context-learning (ICL) paradigms. We hypothesize that this disparity is rooted in language typology: in tonal languages like Chinese, pitch encodes lexical meaning in every syllable (tone), whereas in non-tonal languages like English, pitch carries no lexical function. To test this, we pitch-flattened audio from TAUKADIAL and compared how classification performance changed across both languages. We found that Chinese classification degraded significantly under both zero-shot and ICL conditions (-4.78 and -5.92 UAR, respectively), while English performance increased (+0.11 and +2.98 UAR), implicating tonal pitch as the cross-lingual advantage. These findings suggest language typology should inform the design of audio-based cognitive screening tools, with raw audio preferred for tonal languages and text for non-tonal languages, a distinction critical for developing equitable cross-linguistic screening.

ACL 2026

Tonal Salience in Cognitive Decline: In-Context MCI Detection with Multimodal LLMs

### 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)

Speech-based screening for mild cognitive impairment offers a highly accessible way to detect early cognitive decline. While most existing work focuses on English, cross-linguistic research is emerging to examine how cognitive decline manifests across languages. Studies on the Interspeech'24 TAUKADIAL dataset, comprising English and Chinese speech recordings, consistently report higher classification performance on Chinese, yet the cause of this cross-lingual discrepancy remains unexplored. We examine this gap using Gemini 2.5 Pro, a multimodal large language model, using zero-shot and in-context-learning (ICL) paradigms. We hypothesize that this disparity is rooted in language typology: in tonal languages like Chinese, pitch encodes lexical meaning in every syllable (tone), whereas in non-tonal languages like English, pitch carries no lexical function. To test this, we pitch-flattened audio from TAUKADIAL and compared how classification performance changed across both languages. We found that Chinese classification degraded significantly under both zero-shot and ICL conditions (-4.78 and -5.92 UAR, respectively), while English performance increased (+0.11 and +2.98 UAR), implicating tonal pitch as the cross-lingual advantage. These findings suggest language typology should inform the design of audio-based cognitive screening tools, with raw audio preferred for tonal languages and text for non-tonal languages, a distinction critical for developing equitable cross-linguistic screening.

poster

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.

Tool-using LLM agents are typically compared by accuracy alone, despite deployments being constrained by inference cost. We present a budgeted evaluation of common strategies for improving ReAct-style tool agents (multi-sample aggregation, iterative self-correction, and post-hoc answer revision) using Pareto analysis of cumulative accuracy versus token budget on three benchmarks (HotPotQA, FEVER, GSM8K) with Gemini-2.5-Flash. All experiments use three random seeds ($N{=}500$ per seed); budgeted curves are computed post hoc from per-instance token logs. In our offline evaluation, Reflexion attains the highest accuracy, but its reported token costs are optimistic lower bounds because retries are stopped using ground-truth feedback; deployment costs would be higher. Sampling-based approaches often spend 3--5$\times$ more tokens for comparatively small gains on tool-heavy tasks. GSM8K, a pure-math benchmark with minimal tool interaction, shows dramatically larger gains from all methods, suggesting that the efficiency penalty of repeated tool trajectories is a key factor in tool-heavy settings. We provide a compute-aware evaluation protocol (frontier analysis and marginal-cost metrics) and practical guidance for choosing agent designs under different budget regimes.

What Moves the Pareto Frontier in Tool-Using Agents? A Compute-Aware Study of ReAct Variants

Medical education resources are dense for common diseases but often sparse for under-covered conditions, atypical presentations, and fine-grained concept distinctions. This creates curriculum gaps that are difficult to repair manually, especially in long-tail domains where structured teaching materials are limited. We introduce Curriculum-Gap Completion (CGC), a new task for Large Language Model (LLM)-based medical education in which a model reconstructs missing educational units from a partially specified curriculum graph. Given topic nodes, pedagogical relations, and structured teaching slots, the model predicts omitted concepts, restores missing instructional links, and completes automatically verifiable teaching content. We instantiate this setting in a long-tail medical case study (hyperhidrosis) and evaluate five LLMs under three methods: direct prompting, retrieval-augmented prompting, and our proposed Structure-Aware Curriculum-Gap Completion (SACGC) framework. Across models, SACGC achieves the strongest overall performance, with the largest gains on structurally demanding masking settings. Ablation results show that explicit graph structure is the most important component, while schema constraints provide additional benefit. These findings suggest that LLMs are better suited for reconstructing an under-specified educational structure than for unrestricted medical tutoring, and they motivate CGC as a new natural language processing (NLP) problem for healthcare education.

Filling the Long Tail: Structure-Aware Curriculum-Gap Completion for Medical Education with LLMs

Modern LLMs have demonstrated advanced reasoning skills, including the ability to solve Olympiad-level mathematics problems. While solving more and more difficult problems is a hallmark of LLM progress, less attention has been placed on how "difficulty" is operationalized in the context of LLM problem solving tasks. This is particularly relevant in educational contexts where teachers or students may ask LLMs for "easy" or "hard" questions. In this paper, we explore various quantitative measurements from LLM-generated solutions and evaluate their inter-correlations, as well as their correlation to human-annotated difficulty scores. We find moderate correlations between metrics using log probabilities and output lengths, including some that are more strongly correlated to difficulty than LLM accuracy. We also train ModernBERT to predict difficulty scores, leading to reasonable accuracy within a given benchmark, but decreased performance when generalizing to other math benchmarks. Finally, to explore connections between difficulty scores and human performance, we collect problems, human solutions, and human performance data from the Putnam competition. We find poor alignment between LLM metrics and human-assigned difficulty scores, despite strong correlations between those scores and human performance on the problems.

How Hard is Math? Using Quantitative Metrics to Measure LLM Alignment to Human Intuitions of Difficulty

Frequent revisions of complex regulatory documents in large organizations often introduce inconsistencies and contradictions that are difficult for lawyers and auditors to detect manually. Existing tools rely on character‑level diffs and therefore miss paraphrases and semantic shifts. We introduce LegDiff, a novel benchmark for evaluating span‑aware semantic comparison of legal texts, and use it to investigate the ability of large language models to detect semantic changes beyond token‑ and character‑level matching. LegDiff comprises manually annotated pairs of legal paragraphs drawn from different documents. In addition, we present a pipeline to generate synthetic training data that aligns with the manual annotations and closely resembles real‑world data, and a visualization tool for clearly displaying detected differences and inconsistencies. The dataset, code, and a visualization tool are publicly available to facilitate reproducibility and further research (https://anonymous.4open.science/r/LDC-5BF6/README.md).

Fine-Grained Semantic Comparison of Legal Documents using LLMs

Modern generative AI systems can produce fluent text, clear diagrams, and polished presentations—but they still fail in high-stakes scientific settings. The core issue is not fluency, but the lack of understanding of why content is generated, for whom, and how it should adapt as goals evolve. In this proposal, I argue that effective scientific communication requires modeling user intent, audience variation, and multimodal structure—not just surface quality. To address these gaps, I develop systems across the communication pipeline: ADAPTIVE IE for intent-driven information extraction, GPA and Persona-Aware Slide Generation for audience-aware content adaptation, SciDoc2Diagrammer-MAF for faithful diagram generation, and SMART-Editor for structurally coherent layout refinement. Together, these systems demonstrate that aligning with intent, audience, and structure is essential for meaningful communication. However, existing approaches still lack a principled way to evaluate and generalize usefulness. To address this, I propose three directions: (1) a goal-driven framework to measure the educational utility of document-to-video generation, (2) studying multimodal personalization to improve both creation and comprehension, and (3) building a unified SuperPersonalization benchmark to learn transferable user preferences across tasks. This work shifts the focus from generating content that looks correct to content that actually communicates.

Thesis Proposal: The Missing Why? Building Generative AI That Understands Purpose, Audience, and Context

We argue that LLM-based coding agents frequently fail to solve problems that lie within the model's capacity and the bottleneck is often the conditioning context rather than the model itself. We formalize this for the full class of Turing-computable problems with verifiable specifications and introduce a framework that recasts coding as optimization over a latent space of intentions—natural-language descriptions of high-level solution strategies—and searches this vector space with feedback guidance to steer coding agent toward correct solutions of the problems. The method operates as a plug-in layer that can wrap any coding agent without modifying its architecture or weights. On SWE-Bench Verified, our method raises the resolution rate of a weak, quantized 24B open-weight model to parity with frontier models +25× its size.

Beyond Discrete Search: Divergent Thinking as Optimization in Latent Intention Space

Negotiation involves complex emotional and strategic dynamics that pose challenges for AI agents in negotiation dialogues. This paper proposes a zero-shot soft-labeling method using an large language model-based embedding model and verifies its performance on negotiation dialogues. Furthermore, it examines the performance of predictive model training on rule-based annotated hard and soft labels obtained by the proposed method for the task of predicting whether agreement will be reached from partial dialogues, namely, final disagreement anticipation in negotiation mid-dialogues (FDANMD). Soft labeling obtained by the proposed method showed a maximum HIT@3 score of 0.87 against rule-based annotated hard labels, whereas failure cases also demonstrated the limitations of rule-based annotation. Furthermore, using ROC AUC, evaluations of FDANMD across three datasets (CB, DN, and JI) with negotiation progress rates of 0.25, 0.5, and 1.0 revealed that soft labeling is particularly effective at low negotiation progress rates and also offers superior performance on individual datasets and unseen datasets for models trained on multiple datasets. These results motivate the use of soft labeling to incorporate the complexity of negotiation dialogues into intermediate representations and support the generalizability of zero-shot soft labeling and generalizable predictors across a wide range of negotiations beyond known domains.

LLM-Based Zero-Shot Soft Labeling for Anticipating Disagreement in Negotiation Dialogues

We investigate the extent to which the language processing of LLMs resembles human cognitive processes, focusing on a human cognitive bias called the *neglect-zero effect*. This effect refers to the human tendency to ignore *zero-models*, which are configurations that render a proposition vacuously true by virtue of an empty set. We focus on two types of inference driven by the neglect-zero effect, and examine how LLMs process the inference by comparing their behavior with that in inference not involving the neglect-zero effect. For this purpose, we employ a paradigm using *structural priming*, where recent exposure to a preceding sentence (the *prime*) facilitates the processing of a subsequent sentence (the *target*) due to their structural similarity. We prepare primes so that they force LLMs to consider the zero-model, and analyze whether they also consider zero-models in the target. The results indicate the possibility that the neglect-zero effect does not arise within the LLMs analyzed in this study.

Analysis of the Neglect-Zero Effect in Large Language Models

Constrained decoding systems are often built on context-free parsers intended for programming languages. These parsers either degrade into $O(n^3)$ time-complexity or fail entirely if the grammar is not carefully engineered to keep properties such as determinism and non-ambiguity. There is thus a need to design parsers that efficiently handle non-determinism and ambiguity, while simultaneously being incremental so that they can be coupled with the token-based predictions of large language models. Inspired by prior work, we derive an incremental CYK prefix recognizer, which still has $O(n^3)$ complexity but allows for acceleration with only a fraction of GPU resources (stream multiprocessors). Our parser shows robust efficiency in complex context-free grammars while other parsers crash or degrade. At the same time, we remain empirically competitive in restrictive grammar classes such as LALR.

An Incremental CYK Recognizer for GPU-accelerated General Context-free Prefix Validation

The text-to-table task aims to generate structured data in tabular formats from unstructured text. While the integration of large language models (LLMs) has significantly enhanced the comprehensiveness and flexibility of generation, challenges regarding inconsistent output quality persist, such as the inclusion of redundant information and numerical inaccuracies. We propose TableMBR, a robust table generation method that maintains structural consistency through minimum Bayes risk (MBR) decoding. Experimental results showed that TableMBR outperforms the baseline, achieving relative improvements of up to 15% in F1 score on Rotowire and 23% in accuracy on LiveSum.

Downloads

Next from ACL 2026

What Moves the Pareto Frontier in Tool-Using Agents? A Compute-Aware Study of ReAct Variants

Similar lecture

Using Information Theory to Characterize Prosodic Typology: The Case of Tone, Pitch-Accent and Stress-Accent

.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 2026

What Moves the Pareto Frontier in Tool-Using Agents? A Compute-Aware Study of ReAct Variants

Similar lecture

Using Information Theory to Characterize Prosodic Typology: The Case of Tone, Pitch-Accent and Stress-Accent

Downloads