United States

We find that LoRA fine-tuning exhibits un-learning on contested examples: items with high annotator disagreement show increasing loss during training, a qualitatively distinct pattern largely absent under full fine-tuning and consistent across all six models tested (four encoder, two decoder-only). This discovery emerges from correlating annotation entropy, computed from ChaosNLI&#39;s 100 labels per example, with per-example area under the loss curve (AULC) on SNLI and MNLI. The correlation is positive in all 25 conditions tested (Spearman $\rho = 0.06$-$0.43$), with decoder-only models showing stronger correlations than encoders at matched LoRA rank. The effect survives partial-correlation controls and replicates across seeds and datasets. A preliminary noise-injection experiment is consistent with these findings.

ACL 2026

 Annotation Entropy Predicts Per-Example Learning Dynamics in LoRA Fine-Tuning

## 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!

NAACL 2024

2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics

We find that LoRA fine-tuning exhibits un-learning on contested examples: items with high annotator disagreement show increasing loss during training, a qualitatively distinct pattern largely absent under full fine-tuning and consistent across all six models tested (four encoder, two decoder-only). This discovery emerges from correlating annotation entropy, computed from ChaosNLI's 100 labels per example, with per-example area under the loss curve (AULC) on SNLI and MNLI. The correlation is positive in all 25 conditions tested (Spearman $\rho = 0.06$-$0.43$), with decoder-only models showing stronger correlations than encoders at matched LoRA rank. The effect survives partial-correlation controls and replicates across seeds and datasets. A preliminary noise-injection experiment is consistent with these findings.

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.

**Online Registration Form**: https://acl.swoogo.com/acl2026

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.

Large language models can produce fluent but unfaithful text, known as hallucinations, because point predictions carry no indication of their own reliability. A model that ``knows what it does not know'' could flag, locate, or avoid such failures, yet standard training and decoding offer no such mechanism. Uncertainty is the missing signal, and once calibrated it can serve as a selection filter, an error indicator, or a curriculum guide, three roles unified under a single adaptive-control principle. This thesis develops a framework in which uncertainty is measured from model predictions, calibrated via conformal prediction or analogous principled boundaries, and integrated into the learning or generation process itself. We instantiate this framework in three progressively challenging scenarios: classification under label noise (uncertainty as selection), video generation (uncertainty as error correction), and text generation (uncertainty as curriculum). The principle is validated in classification and video generation and extended to text generation, showing that the pipeline structure is invariant while each component takes qualitatively new forms under escalating difficulty.

Thesis Proposal: Uncertainty as Adaptive Control: From Selection to Curriculum via Conformal Calibration

One partner says "Fine" meaning resolution; the other hears surrender. The word is shared; the affective uptake is not. We formalize this as **affective meaning divergence** (AMD), the total-variation distance between interlocutors' anchor-conditioned affect distributions. Building on speech-act theory, common-ground accumulation, and entropy-regularized game theory, we derive a logit best-response map whose dynamics undergo a *saddle-node bifurcation*: when $\beta\alpha > 4$, a monotone increase in AMD-driven load produces an abrupt, hysteretic collapse of repair coordination. On Conversations Gone Awry (CGA-Wiki; $N=652$), derailing conversations exhibit critical-slowing-down (CSD) signatures across multiple levels: lexical divergence variance ($p<0.001$, $d=0.36$), AMD variance ($p=0.001$, $d=0.26$), and dialog-act repair variance ($p=0.016$, $d=0.20$), all significant after correction and stronger than toxicity and sentiment baselines. AMD provides a distinct temporal signature, with retrospectively measured variance peaking at the bifurcation point while toxicity variance peaks earlier, and is the only indicator grounded in the theoretical framework. Boundary-condition analysis on CGA-CMV ($N=1,169$) yields mixed but directionally consistent evidence.

Phase Transitions in Affective Meaning Divergence: The Hidden Drift Before the Break

Reasoning models frequently agree with incorrect user suggestions - a behavior known as sycophancy. However, it is unclear where in the reasoning trace this agreement originates and how strong the commitment is. We introduce sycophantic anchors - sentences identified via counterfactual analysis that commit models to user agreement. Across four reasoning models spanning three architecture families (Llama, Qwen, Falcon-hybrid) and 1.5B - 8B parameters, we analyze over 200,000 counterfactual rollouts and show that linear probes reliably detect sycophantic anchors (74 - 85\% balanced accuracy), outperforming text-only baselines at high commitment levels - confirming they capture internal states beyond surface vocabulary. Regressors further predict commitment strength from activations ($R^2$ up to 0.74). We observe a consistent asymmetry: sycophancy leaves a stronger mechanistic footprint than correct reasoning. We also find that sycophancy builds gradually during generation rather than being determined by the prompt. These findings enable sentence-level detection and quantification of model misalignment mid-inference.

Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning Models

Hate speech detection is essential for maintaining healthy online communities. Large language models (LLMs) perform well on text classification, yet their decision strategies need to be better understood. While post-hoc rationales can justify individual decisions, they substantially increase inference cost and limit scalability in high-throughput settings. As another approach, we propose an extended rational inattention model that parameterizes linguistic noise and information processing cost, providing an interpretable behavioral framework for black-box LLM classifiers. Treating LLMs as rational decision-makers under information constraints allows us to estimate - from the observed classification behavior - the parameters that represent information processing cost and noise sensitivity. As a case study and using a hate-speech dataset spanning multiple noise environments, we evaluate four commercial LLMs and show that the introduced extended rational inattention model predictions closely match the observed performance across different noise levels. We further test the performance under various noise mechanisms and find that the inferred information cost parameters remain consistent while the noise parameters vary with the distortion mechanism. Overall, our introduced framework offers a cost-efficient and quantitative approach to derive interpretable indices of LLM moderation behavior and decisions, without additional rationale generation.

Interpretability of LLM Classifiers via the Rational Inattention Theory with Application to Hate Speech Detection

Adversarial perturbations in the context of large language models (LLMs) are subtle changes added to input data (i.e., images or text) that are designed to alter predictions or outputs of machine learning models. We introduce several novel visualizations using topological data analysis (TDA) (leveraging persistent homology) to characterize how adversarial perturbations act on text inputs, specifically, how sandbagging and code-injection attacks alter the geometric structure of attention heads in transformer models. By computing persistent homology metrics from attention maps across different model architectures (such as BERT, RoBERTa, ELECTRA, DistilGPT, etc.), we find that adversarial inputs alter higher-dimensional topological features ($H_{1}$ loops and $H_{2}$ voids) in ways that distinguish them from clean, non-adversarial inputs.

The Shape of Vulnerability: How Adversarial Perturbations Reshape the Topology of Language Model Latent Spaces

We propose a novel approach to translating Japanese slides into English and to correcting their layout errors by utilizing multimodal LLMs with slide images and XML structures. Existing translation tools often suffer from layout errors after translation due to text expansion during the translation process, causing text to overlap with figures or other items in slides and thereby reducing readability. To overcome this issue, our proposed framework introduces two steps consisting of (i) translating text fragments within the slide, and (ii) correcting layout errors by optimizing layout placement based on visual consistency. In step (ii), we empirically show that few-shot prompts are quite effective in layout error correction. Given that the optimal combination of steps (i) and (ii) varies depending on the slide layout, our method generates eight different layout candidates. Consequently, we introduce a third step that automatically selects the optimal output from these eight candidates. The experimental results showed that the proposed method outperformed baselines and achieved 4.1% layout error rate and over 80% model selection success rate.

Presentation Slide Translation and Layout Error Correction by LLMs

Rap is a vocal style rooted in Hip-Hop culture, characterized by producing rhymes in synchrony with a rhythmic beat. This paper proposes a method for generating Japanese rap lyrics with a large language model (LLM) whose rhyming behavior is improved via reinforcement learning. We design a reward function that evaluates end rhymes between two generated bars and apply GRPO, a reinforcement-learning method, to encourage Japanese rhyming without using existing Japanese rap lyrics as training data. Experimental results show that, although output collapse is observed in some cases, GRPO increases the proportion of outputs that receive moderate or high human ratings on rhyme-related criteria.

Constructing a Japanese Rap Lyric Generation Model with GRPO

To prepare for an uncertain future, organizations must continuously monitor emerging trends and early signals of change. The increasing availability of web-based textual data has boosted natural language processing (NLP) methods in strategic foresight, particularly in the scanning phase. While prior studies have extensively focused on the identification of trends and weak signals in such data, considerably less attention has been paid to how these signals evolve over time and gain relevance as they become more visible. This study addresses this gap by examining whether tracking the temporal dynamics of signals can improve their assessment for strategic decision-making. Using a large-scale web news corpus, we apply established neural topic modeling and clustering techniques to extract and link semantically coherent signals across time. By examining the resulting cluster trajectories, we analyze how newly emerging signals intensify and potentially mature into more established trends. Demonstrated on the use case of the European electric vehicle market, we find three dominant signal trajectories and show that burst dynamics tend to surface signal consolidation rather than the early detection of weak signals. By showing that signals reoccur at irregular intervals and gain strategic relevance through evolving developments, the results indicate that foresight research should move beyond static, one-off analyses toward a dynamic temporal perspective capable of identifying signals at earlier stages of emergence. From a managerial perspective, the findings underscore the need for frameworks that systematically surface signals from external environments and enable timely strategic responses by integrating expert knowledge to support proactive decision-making and adaptation ahead of major environmental shifts.

Tracking the Evolution of Foresight Signals in News Data: The Case of the European Electric Vehicle Market

Large Language Models (LLMs) often exhibit homogenized cultural perspectives. While the World Values Survey (WVS) provides a gold standard for mapping human values, traditional direct prompting of LLMs on WVS often fails to access the model's latent cultural depth, leading to safety-aligned refusals or neutral responses. Here, we propose a generalizable framework for cultural evaluation and intervention that transitions from abstract queries to scenario-based behavioral probing. By extracting implicit token probabilities across 300 situational dilemmas, we bypass surface-level alignment to map the latent coordinates of LLMs cultural value. We further introduce activation steering to shift these internal alignments during the forward pass without retraining. Our results reveal that cultural adaptability is non-uniform. While Llama exhibits structural rigidity, Qwen and Gemma show high but volatile sensitivity across social domains such as family and the legal system. Finally, we quantify latent entanglement, demonstrating that models encode cultural axes as coupled ``modernization'' dimensions. This work establishes a computationally efficient framework for cultural steering, highlighting the structural complexities when navigating global value with LLMs.

Cultural Value Alignment Via Latent Activation Steering in Large Language Models

The Advanced Encryption Standard (AES) is currently considered the preferred standard of encryption for secure messaging by the National Institute of Standards and Technology. While its predecessor, the Data Encryption Standard (DES), can be analyzed in mere seconds with modern cryptanalysis algorithms, those same algorithms are unfeasible for cryptanalysis of AES. This is primarily because the key, or the list of values used during encryption, was increased from a length of 56 bits to 128 bits. The list of all possible combinations, also called the probability space, is tens of magnitudes larger in AES than DES. Current DES cryptanalysis methods use mathematical methods to find the most statistically likely approximate key in the entire probability space. The increased probability space in AES is too large to find an approximation using these formulas. However, these methods operate under the assumption that every key is possible. While this is mathematically true, when looked at from the lens of a linguist, many of these keys create messages that are impossible in language. Linguistic attestation is the documentation that a word, grapheme, sound, or other linguistic feature exists in a language. This thesis proposal presents an algorithm that eliminates AES keys using linguistic attestation. I apply the idea that any grammatical message encrypted by AES will not contain any "unattested" data in its input. The algorithm proposes trimming the probability space by removing keys that are unattested. Once a smaller probability space has been created, any method that searches the probability space for a solution may be applied to find the key from the new, smaller list of filtered keys.

Downloads

Next from ACL 2026

Thesis Proposal: Uncertainty as Adaptive Control: From Selection to Curriculum via Conformal Calibration

Similar lecture

Low-Rank Adaptation for Multilingual Summarization: An Empirical Study

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

Thesis Proposal: Uncertainty as Adaptive Control: From Selection to Curriculum via Conformal Calibration

Similar lecture

Low-Rank Adaptation for Multilingual Summarization: An Empirical Study

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads