United States

The expanding long-context capabilities of large language models are constrained by a significant memory bottleneck: the key-value (KV) cache required for autoregressive generation. This bottleneck is substantial; for instance, a Llama-3.1-8B model processing a 32K-token prompt at a batch size of 4 requires approximately 16 GB for its KV cache, exceeding the model&#39;s weights. While KV-cache compression via low-rank projection is promising, existing methods rely on a static, offline-learned subspace that performs poorly under distribution shifts. To overcome these limitations, we introduce OjaKV, a novel framework integrating a hybrid storage policy with online subspace adaptation. OjaKV preserves crucial tokens in full rank as high-fidelity anchors, while applying low-rank compression to intermediate tokens by adapting the projection basis using Oja&#39;s algorithm for online PCA. This adaptation involves a comprehensive update during prefilling and lightweight periodic updates during decoding, ensuring the subspace remains aligned with evolving context. Our framework is fully compatible with FlashAttention. Experiments demonstrate that OjaKV maintains or improves zero-shot accuracy at high compression ratios, achieving the strongest gains on long-context benchmarks requiring complex reasoning. Furthermore, our approach combines with token-selection methods for compounded memory savings, establishing a practical, plug-and-play solution for memory-efficient long-context inference without fine-tuning.

ACL 2026

 OjaKV: Context-Aware Online Low-Rank KV Cache Compression

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

The expanding long-context capabilities of large language models are constrained by a significant memory bottleneck: the key-value (KV) cache required for autoregressive generation. This bottleneck is substantial; for instance, a Llama-3.1-8B model processing a 32K-token prompt at a batch size of 4 requires approximately 16 GB for its KV cache, exceeding the model's weights. While KV-cache compression via low-rank projection is promising, existing methods rely on a static, offline-learned subspace that performs poorly under distribution shifts. To overcome these limitations, we introduce OjaKV, a novel framework integrating a hybrid storage policy with online subspace adaptation. OjaKV preserves crucial tokens in full rank as high-fidelity anchors, while applying low-rank compression to intermediate tokens by adapting the projection basis using Oja's algorithm for online PCA. This adaptation involves a comprehensive update during prefilling and lightweight periodic updates during decoding, ensuring the subspace remains aligned with evolving context. Our framework is fully compatible with FlashAttention. Experiments demonstrate that OjaKV maintains or improves zero-shot accuracy at high compression ratios, achieving the strongest gains on long-context benchmarks requiring complex reasoning. Furthermore, our approach combines with token-selection methods for compounded memory savings, establishing a practical, plug-and-play solution for memory-efficient long-context inference without fine-tuning.

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.

Class imbalance is a widespread challenge in NLP tasks, significantly hindering robust performance across diverse domains and applications. 
We introduce Hardness-Aware Meta-Resample (HAMR), a unified framework that adaptively addresses both class imbalance and data difficulty. 
HAMR employs bi-level optimizations to dynamically estimate instance-level weights that prioritize genuinely challenging samples and minority classes, while a neighborhood-aware resampling mechanism amplifies training focus on hard examples and their semantically similar neighbors. 
We validate HAMR on six imbalanced datasets covering multiple tasks and spanning biomedical, disaster response, and sentiment domains. 
Experimental results show that HAMR achieves substantial improvements for minority classes and consistently outperforms strong baselines. 
Extensive ablation studies demonstrate that our proposed modules synergistically contribute to performance gains and highlight HAMR as a flexible and generalizable approach for class imbalance adaptation.

Model-Agnostic Meta Learning for Class Imbalance Adaptation

The systematicity of natural language interpretation—our ability to understand novel expressions by compositionally combining familiar elements—has been central to debates about symbolic versus neural approaches to cognition since Fodor and Pylyshyn (1988). We investigate whether artificial neural networks can learn model-theoretic interpretation functions that generalize systematically to out-of-training-sample sentences, framing interpretation as an encoding task from discrete linguistic input to continuous truth-conditional representations. We extend Frank et al. (2009) with entity-level semantic representations, modern architectures (GRU, LSTM, Attention with AbsPE/RoPE), principled competing event generation, extended systematicity tests (∼350 vs. ∼80 sentences), and a two- dimensional difficulty analysis disaggregating results by modifier complexity. Across 140 trained models (7 architectures), we find that capacity-matched architectures perform comparably on easy tests, but gated recurrent networks (GRU and LSTM) significantly outperform transformer architectures on the hardest compositional generalization test (Basic Event), while ungated SRN does not—indicating that the gating mechanism is a critical factor. Entity vectors significantly improve scores on Basic Event across most architectures, with gated architectures benefiting most, validating formal semantics’ treatment of entities as important theoretical primitives. The extended test set reveals that systematicity difficulty has two dimensions: the type of systematicity test (as in Frank et al. 2009), and the number of modifiers being composed.

The Learnability of Model-Theoretic Interpretation Functions in Artificial Neural Networks

Machine unlearning is becoming essential for building trustworthy and compliant language models. Yet unlearning success varies considerably across individual samples: some are reliably erased, while others persist despite the same procedure. We argue that this disparity is not only a data-side phenomenon, but also reflects model-internal mechanisms that encode and protect memorized information. 
We study this problem from a mechanistic perspective based on model circuits--structured interaction pathways that govern how predictions are formed. We propose Circuit-guided Unlearning Difficulty (\metric), a {\em pre-unlearning} metric that assigns each sample a continuous difficulty score using circuit-level signals. Extensive experiments demonstrate that \metric reliably separates intrinsically easy and hard samples, and remains stable across unlearning methods. We identify key circuit-level patterns that reveal a mechanistic signature of unlearning difficulty: easy-to-unlearn samples are associated with shorter, shallower interactions concentrated in earlier-to-intermediate parts of the original model, whereas hard-to-unlearn samples rely on longer and deeper pathways closer to late-stage computation. Compared to existing qualitative studies, \metric takes a first step toward a principled, fine-grained, and interpretable analysis of unlearning difficulty; and motivates the development of unlearning methods grounded in model mechanisms.

A Mechanistic Perspective and Difficulty Metric for Unlearning

In-context learning (ICL) performance depends critically on which demonstrations are placed in the prompt, yet most existing selectors prioritize heuristic notions of relevance or diversity and provide limited insight into the $\textbf{coverage}$ of a demonstration set. We propose $\textbf{Unseen Coverage Selection (UCS)}$, a training-free, subset-level coverage prior motivated by the principle that a good demonstration set should $\textbf{expose the model to latent cluster unrevealed by the currently selected subset}$. UCS operationalizes this idea by $\textbf{(1)}$ inducing discrete latent $\textbf{clusters}$ from model-consistent embeddings and $\textbf{(2)}$ estimating the number of unrevealed clusters within a candidate subset via a Smoothed Good-Turing estimator from its empirical frequency spectrum. Unlike previous selection methods, UCS is coverage-based and training-free, and can be seamlessly combined with both query-dependent and query-independent selection baselines via a simple regularized objective. Experiments on multiple intent-classification and reasoning benchmarks with frontier Large Language Models show that augmenting strong baselines with UCS consistently improves ICL accuracy by up to $\textbf{2-6}$% under the same selection budget, while also yielding insights into task- and model-level latent cluster distributions. Code is available at https://github.com/Raina-Xin/UCS.

UCS: Estimating Unseen Coverage for Improved In-Context Learning

When a student fails an exam, do we tend to blame their effort or the test’s difficulty? Attribution, defined as how reasons are assigned to event outcomes, shapes perceptions, reinforces stereotypes, and influences decisions. Attribution Theory explains how people attribute causes to internal factors (effort, ability) or external ones (task difficulty, luck). LLMs' attribution of event outcomes based on demographics carries important fairness implications. Most works exploring social biases in LLMs focus on surface-level associations or isolated stereotypes. This work proposes a cognitively grounded bias evaluation framework to identify how models’ reasoning disparities shape demographic bias across three contexts: single-actor, actor–actor, and actor–observer, capturing comparative and perspective-driven biases overlooked in prior work. Introducing a 140k-prompt benchmark covering ten scenarios and four social dimensions, our analyses reveal attribution asymmetries across identities that vary in multi-actor and observer settings, suggesting that other identities influence bias. This work underscores the need for cognitively grounded bias evaluation and informs future debiasing efforts through the proposed framework.

 Talent or Luck? Evaluating Attribution Bias in Large Language Models

Most existing dialogue systems are user-driven, primarily designed to fulfill user requests. However, in many critical real-world scenarios, a conversational agent must proactively extract information to achieve its own objectives rather than merely respond. To address this gap, we introduce Inquisitive Conversational Agents (ICAs) and develop an ICA specifically tailored to U.S. Supreme Court oral arguments. We propose a Dual Hierarchical Reinforcement Learning framework featuring two cooperating RL agents, each with its own policy, to coordinate strategic dialogue management and fine-grained utterance generation. By learning when and how to ask probing questions, the agent emulates judicial questioning patterns and systematically uncovers crucial information to fulfill its legal objectives. Evaluations on a U.S. Supreme Court dataset show our method outperforms single-agent RL baselines in multiple metrics. Although specialized to a single legal domain, it represents an important first step toward broader high-stakes, domain-specific applications. We attached a part of the code as supplementary material. All code will be released upon publication for reproducibility.

Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents

Self-supervised speech models (S3Ms) are known to encode rich phonetic information, yet how this information is structured remains underexplored. We conduct a comprehensive study across 96 languages to analyze the underlying structure of S3M representations, with particular attention to phonological vectors.
We first show that there exist linear directions within the model's representation space that correspond to phonological features. We further demonstrate that the scale of these phonological vectors correlate to the degree of acoustic realization of their corresponding phonological features in a continuous manner. For example, the difference between [d] and [t] yields a voicing vector: adding this vector to [p] produces [b], while scaling it results in a continuum of voicing. Together, these findings indicate that S3Ms encode speech using phonologically interpretable and compositional vectors, demonstrating phonological vector arithmetic.
All code and interactive demos are available at https://github.com/juice500ml/phonetic-arithmetic.

 [b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic

Safety guardrails in large language models (LLMs) are developed to prevent malicious users from generating toxic content at a large scale. However, these measures can inadvertently introduce or reflect new biases, as LLMs may refuse to generate harmful content targeting some demographic groups and not others. We explore this selective refusal bias in LLM guardrails through the lens of refusal rates of targeted individual and intersectional demographic groups, types of LLM responses, and length of generated refusals. Our results show evidence of selective refusal bias across gender, sexual orientation, nationality, and religion attributes. This leads us to investigate additional safety implications via an indirect attack, where we target previously refused groups, and find that Llama 3.1 fails to defend against our attack in roughly 89% of the trials. Our findings emphasize the need for more equitable and robust performance in safety guardrails across demographic groups.

 Characterizing Selective Refusal Bias in Large Language Models

Knowledge-Based Visual Question Answering (KB-VQA) requires grounding visual queries to external knowledge beyond directly observable content in images.
While recent multi modal large language models (MLLMs) show strong perceptual abilities, they struggle on KB-VQA tasks requiring groundings from both fine-grained entity and evidence levels.
Most existing multi-modal retrieval augmented generation (MM-RAG) methods tightly couple entity discrimination and section-level evidence ranking into a single re-ranking stage, leading to high cost and limited generalization.
In this work, we revisit existing MM-RAG solutions from a workflow perspective and argue both entity-level and fact-level groundings are key bottlenecks.
We observe that although MLLMs often fail under open-ended entity naming, they can better identify the correct entity when selecting from a small set of candidate names.
Based on this insight, we propose a simple and training-free identify-before-answer IBA framework that decouples entity identification from section-level re-ranking.
Our approach prompts an MLLM to select high-confidence entities using only candidate names, followed by an off-the-shelf textual re-ranker for evidence selection.
Experiments on Encyclopedic-VQA and InfoSeek show that our method consistently outperforms fine-tuned multi-modal re-ranking baselines while reducing training and inference complexity.
Additional analyses reveal that the improvements arise not only from better entity identification, but also from selecting more informative evidence once correct entity is fixed.
Our implementation is made public to ease reproducibility

Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification

We present a neuromuscular speech interface that translates silently voiced articulations directly into text. We record surface electromyographic (EMG) signals from multiple articulatory sites on the face and neck as participants *silently* articulate speech, enabling direct EMG-to-text translation. Such an interface has the potential to restore communication for individuals who have lost the ability to produce intelligible speech due to laryngectomy, neuromuscular disease, stroke, or trauma-induced damage (e.g., radiotherapy toxicity) to the speech articulators. Prior work has largely focused on mapping EMG collected during *audible* articulation to time-aligned audio targets or transferring these targets to *silent* EMG recordings, which inherently requires audio and limits applicability to patients who can no longer speak. In contrast, we propose an efficient representation of high-dimensional EMG signals and demonstrate direct sequence-to-sequence EMG-to-text conversion at the phonemic level without relying on time-aligned audio.

Downloads

Next from ACL 2026

Model-Agnostic Meta Learning for Class Imbalance Adaptation

Similar lecture

Eigen Attention: Attention in Low-Rank Space for KV Cache Compression

Stay up to date with the latest Underline news!

PRODUCT

COMPANY

RESOURCES