United States

Training Large Language Models (LLMs) relies predominantly on written, curated corpora, which may limit their reliability on spontaneous speech. Oral language exhibits real-time planning markers — filled pauses, repetitions, false starts, and vowel lengthenings — that modulate epistemic commitment. This pilot study investigates how such disfluencies affect the alignment between LLM confidence and a discourse-pragmatic uncertainty proxy in a Portuguese model (Llama-3.1-8B-Instruct). Using a benchmark of 344 turns from the Roda Viva corpus, we contrast faithful Conversation Analysis transcriptions with sanitized versions and combine binned divergence metrics (ECE, OE) with rank correlation and multivariate regression analyses. We find that model confidence is overwhelmingly driven by a surface feature — turn length (${\beta_{\text{std}}} = +14.47, p &lt; 0.001$) — rather than by pragmatic markers of uncertainty (${\beta_{\text{oral}}} = -3.09, {\beta_{\text{hedges}}} = -0.97$, both non-significant; $R^2 = 0.29$). After controlling for length, residual effects of disfluency markers align in the human-expected direction but are dwarfed by length bias. We argue that this surface-feature dominance subsumes the pragmatic blindness phenomenon and explains the substantial divergence observed via ECE (41.95) and OE (4.29) between faithful and sanitized conditions.

ACL 2026

Speech Disfluencies and LLM Confidence: Length Bias and Pragmatic Insensitivity in Brazilian Portuguese

surface-feature dominance

pragmatic blindness

speech disfluencies

llm calibration

brazilian portuguese

computational linguistics

### 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)

Training Large Language Models (LLMs) relies predominantly on written, curated corpora, which may limit their reliability on spontaneous speech. Oral language exhibits real-time planning markers — filled pauses, repetitions, false starts, and vowel lengthenings — that modulate epistemic commitment. This pilot study investigates how such disfluencies affect the alignment between LLM confidence and a discourse-pragmatic uncertainty proxy in a Portuguese model (Llama-3.1-8B-Instruct). Using a benchmark of 344 turns from the Roda Viva corpus, we contrast faithful Conversation Analysis transcriptions with sanitized versions and combine binned divergence metrics (ECE, OE) with rank correlation and multivariate regression analyses. We find that model confidence is overwhelmingly driven by a surface feature — turn length (${\beta_{\text{std}}} = +14.47, p < 0.001$) — rather than by pragmatic markers of uncertainty (${\beta_{\text{oral}}} = -3.09, {\beta_{\text{hedges}}} = -0.97$, both non-significant; $R^2 = 0.29$). After controlling for length, residual effects of disfluency markers align in the human-expected direction but are dwarfed by length bias. We argue that this surface-feature dominance subsumes the pragmatic blindness phenomenon and explains the substantial divergence observed via ECE (41.95) and OE (4.29) between faithful and sanitized conditions.

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.

Recent work representing discourse relations such as "cause" or "concession" in the framework of eRST has connected hierarchical discourse parsing to explicit connectives, such as 'because' or 'although', bringing the framework closer to lexicalized shallow parsing in the tradition of PDTB. However, while PDTB postulates implicit, unexpressed connectives (i.e. an implied 'although' etc.), no such devices are recognized in eRST, and consequently next to nothing is known about the relationship between PDTB-style implicit connectives and eRST-style discourse graphs. In this paper we propose and evaluate an algorithm to align eRST data, which already indicates explicit connectives, to implicit connective annotations following the PDTB guidelines. We also conduct the first evaluation of the relationship between hierarchical RST-style relations and PDTB implicit connectives.

DM Doppelgangers: Implicit Connectives as eRST Signals

In this paper, we present a descriptive corpus analysis of bridging anaphora across 16 genres of English, leveraging the multi-genre GUMBridge corpus for varieties of bridging anaphora. We begin our investigation by examining the distribution of bridging instances by sub-varieties and across genres, finding that spoken genres have less bridging instances than written ones. We then investigate the linguistic environments of bridging anaphora and their corresponding associative antecedents in the underlying data of the corpus, examining both categorical features (entity type, part of speech, syntactic dependency relations) and numeric features (mention length, cluster size, salience, and distance between the bridging anaphor and antecedent). We find bridging anaphora have a tendency to be shorter and are more often definite, and bridging antecedents show tendency to be more salient than other entities. Finally, we analyze how several of the numeric features of bridging environments vary by genre, finding consistency across genres for observed trends in the environments of bridging anaphora and antecedents.

What's in a Bridge?: A Descriptive, Multi-Genre Analysis of the GUMBridge Corpus for Varieties of Bridging Anaphora

Crowd-sourcing implicit discourse relations has been shown to yield a variety of plausible interpretations, but also to be prone to annotation errors. In this study, we apply the dataset cartography technique (Swayamdipta et al., 2020) to implicit discourse relations. We find that error identification via low confidence is infeasible for IDRR datasets; 
however, high confidence in models coincides with strong textual heuristics and with high item-wise agreement, pointing to shortcut use by models and, partly, by crowd workers. Balancing out this factor is required to ensure robust IDRR learning and evaluation.

Dataset Cartography for IDRR: Promises and Pitfalls

This paper introduces a novel 'universal' approach to discourse annotation, serving as a comprehensive synthesis of the ISO 24617-8 semantic annotation framework and a newly developed multi-layer model of coherence relations. To address the complexities of text analysis, we present a hierarchical classification and a systematic decision tree. By unifying disparate formalisms, our model provides researchers with a robust, standardised methodology for analysing complex discourse structures across various linguistic contexts.

Universal Discourse Relations: A Proposal

This abstract describes a work-in-progress study of conversation-level effects on in-context word meaning. The abstract describes a definition modeling-based metric for lexical semantic conversational contingency and presents the results of a pilot study using the Fora corpus.

Investigating discourse-level lexical semantic adaptation: A definition modeling approach

In this work, we propose a method for dialog simulation to gather high-quality open-domain, multi-turn question answering conversations. The simulation is grounded on Stack Exchange posts and motivated by computational discourse theory. We first convert forum posts into structured directed graphs; then, different traversals through the graph represent possible conversational trajectories. Our proposed graph traversal algorithm produces dialogs optimized for conversational efficiency. In addition, we propose an evaluation framework based on Gricean conversational maxims. Expert-level human annotators evaluate transcripts according to our framework; dialogs produced by our method receive ratings that are competitive with dialogs from prior work.

A First Step towards Dialog Simulation with Grounded Dialog Graphs

This extended abstract presents a Rational Speech-Act model predicting the persuasiveness ("argument strength") of explanations, as well as preliminary experimental data that validates the predictions of the model. While first-order Bayesian models developed by psychologists of reasoning generally predict that arguments become stronger when more reasons are provided, we investigate the competing intuition that excess reasons can weaken an argument ("the lady doth protest too much!"). We account for this effect by drawing upon a growing body of literature which shows that listeners make pragmatic inferences to rationalize violations of their "informativity expectations".

The lady doth protest too much: discourse expectations affect judgments of argument strength

We present semantic-pragmatic specification and annotation (ellipsis, coreference, bridging and discourse relations, information structure, scope of negation) in the multi-layer, genre-diversified, 3+ million-token Enriched PDT. While morphology and syntax work almost exclusively on sentence level, the semantic-pragmatic phenomena are often related to two or more neighbouring sentences and possibly to an extra-linguistic context. In the contribution, we describe these phenomena from both the linguistic perspective (form of expression, relation to syntax and morphology) and the cognitive perspective (relation to context, real world knowledge, as well as to the related processes such as thinking or reasoning) – classifying the possible relations between the semantic-pragmatic units into cognitively plausible, distinguishable, and human-understandable categories. We have applied our results to the corpus, by annotating it in its entirety. The resulting Enriched PDT is publicly and freely available, to serve for verification and further investigation of (not only) these phenomena.

Semantic-pragmatic Annotations in the Prague Dependency Treebank

Errors in automatic coreference resolution can be traced back to errors in mention detection and coreference linking. In this paper, we analyse the errors in mention detection produced by the coreference resolver CorPipe (Straka 2023). In particular, we evaluate the performance on different variants of German (written, spoken, original, and simplified). We discuss the errors against the background of the fact that the tool was trained on a combination of different coreference corpora, including two German datasets with partially conflicting annotation guidelines. The results indicate that simplification has a significant effect on mention detection independent of the modality.

Errors in coreference resolution in German: Effects of modality, simplification and heterogeneous training data

We introduce BeDiscovER (Benchmark of Discourse Understanding in the Era of Reasoning Language Models), an up-to-date, comprehensive suite for evaluating the discourse-level knowledge of modern LLMs. BeDiscovER compiles 5 publicly available discourse tasks across discourse lexicon, (multi-)sentential, and documental levels, with in total 52 individual datasets. It covers both extensively studied tasks such as discourse parsing and temporal relation extraction, as well as some novel challenges such as discourse particle disambiguation (e.g., “just”), and also aggregates a shared-task on Discourse Relation Parsing and Tree-banking for multilingual and multi-framework discourse relation classification. We evaluate open-source LLMs: Qwen3 series, DeepSeek-R1, and frontier reasoning model GPT-5-mini on BeDiscovER, and find that state-of-the-art models exhibits strong performance in arithmetic aspect of temporal reasoning, but they struggle with long-dependency reasoning and some subtle semantic and discourse phenomena, such as rhetorical relation classification.

Downloads

Next from ACL 2026

DM Doppelgangers: Implicit Connectives as eRST Signals

Similar lecture

Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models’ Uncertainty?

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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

DM Doppelgangers: Implicit Connectives as eRST Signals

Similar lecture

Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models’ Uncertainty?

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads