Austria

Emerging Large Language Model (LLM) applications require long input context in order to perform complex tasks like document analysis and code generation.
For these long context length applications, the length of the input prompt poses a significant challenge in terms of inference efficiency since the inference costs increase linearly with sequence length.
However, for many of these applications, much of the context in the prompt is fixed across different user inputs, thereby providing the opportunity to perform offline optimizations in order to process user inputs quickly, as they are received. 
We propose Squeezed Attention to accelerate LLM applications where a large portion of the input context is fixed.
We first leverage K-means clustering offline to group the keys for the fixed context based on semantic similarity and represent each cluster with a single centroid value.
During inference, we compare query tokens from the user input with the centroids to predict which keys from the fixed context are semantically relevant, and then compute exact attention using only the important keys, thereby reducing bandwidth and computational costs. 
We also present a hierarchical version of our algorithm which can reduce the complexity of attention from linear to logarithmic with respect to the fixed context length.
We evaluate our method on various long-context benchmarks including LongBench, where it achieves a 3.1$\times$ reduction in KV budget with no noticeable accuracy loss and up to an 8$\times$ reduction with only a 0.5 point accuracy gap for the LLaMA-2-7B-32K, LWM-Text-Chat-1M, and Longchat-7B-v1.5-32K models.
Futhermore, we implement kernels for centroid comparison and sparse FlashAttention with important keys, achieving more than 4$\times$ speedups during both the prefill and generation phases for long-context inference.
Our code is available at https://github.com/SqueezeAILab/SqueezedAttention.

ACL 2025

Squeezed Attention: Fast Fixed Context Processing for Long Context Length LLM Applications

ml systems

efficient llm inference

long context

## 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.

poster

### 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**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

In this paper, we introduce \textit{\textbf{SAIL}-VL} (\textit{\textbf{S}c\textbf{A}lable Vision Language Model Tra\textbf{I}ning via High Qua\textbf{L}ity Data Curation}), an open-source vision language model (VLM) series achieving state-of-the-art (SOTA) performance in 2B and 8B parameters. The following three key improvements contribute to SAIL-VL's leading performance: (1) Scalable high-quality visual understanding data construction: We implement a data construction pipeline to enable hundred-million-scale high-quality recaption data annotation. The resulted dataset SAIL-Caption is validated to be of the highest data quality compared with opensource datasets. (2) Scalable Pretraining with High-Quality Visual Understanding Data: We scale SAIL-VL's pretraining budget up to 655B tokens and show that even a 2B VLM benefits from scaled up training data sizes, exhibiting logarithmic data size scaling laws in benchmark performance. (3) Scalable SFT via data quantity and complexity scaling: We curate a high-quality SFT dataset collection with leading data quantity scaling effectiveness and demonstrate that training with progressively higher-complexity data surpasses baseline one-stage training by a large margin. 

SAIL-VL series models achieve the highest average score in 18 widely used VLM benchmarks in our evaluation, with the 2B model takes the top position over VLMs of comparable sizes on OpenCompass 2024 (https://rank.opencompass.org.cn/leaderboard-multimodal), demonstrating robust visual comprehension abilities. SAIL-VL series models are released at HuggingFace (https://huggingface.co/BytedanceDouyinContent).

Scalable Vision Language Model Training via High Quality Data Curation

Multi-head Latent Attention (MLA) is an innovative architecture proposed by DeepSeek, designed to ensure efficient and economical inference by significantly compressing the Key-Value (KV) cache into a latent vector. Compared to MLA, standard LLMs employing Multi-Head Attention (MHA) and its variants such as Grouped-Query Attention (GQA) exhibit significant cost disadvantages. Enabling well-trained LLMs (e.g., Llama) to rapidly adapt to MLA without pre-training from scratch is both meaningful and challenging. This paper proposes the first data-efficient fine-tuning method for transitioning from MHA to MLA (**MHA2MLA**), which includes two key components: for *partial-RoPE*, we remove RoPE from dimensions of queries and keys that contribute less to the attention scores, for *low-rank approximation*, we introduce joint SVD approximations based on the pre-trained parameters of keys and values. These carefully designed strategies enable MHA2MLA to recover performance using only a small fraction (0.6\% to 1\%) of the data, significantly reducing inference costs while seamlessly integrating with compression techniques such as KV cache quantization. For example, the KV cache size of Llama2-7B is reduced by 92.19\%, with only a 1\% drop in LongBench performance. Our source code is publicly available at https://github.com/JT-Ushio/MHA2MLA.

Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs

Visual Language Models (VLMs) demonstrate impressive capabilities in processing multimodal inputs, yet applications such as visual agents, which require handling multiple images and high-resolution videos, demand enhanced long-range modeling. Moreover, existing open-source VLMs lack systematic exploration into extending their context length, and commercial models often provide limited details. To tackle this, we aim to establish an effective solution that enhances long context performance of VLMs while preserving their capacities in short context scenarios. Towards this goal, we make the best design choice through extensive experiment settings from data curation to context window extending and utilizing: (1) we analyze data sources and length distributions to construct ETVLM - a data recipe to balance the performance across scenarios; (2) we examine existing position extending methods, identify their limitations and propose M-RoPE++ as an enhanced approach; we also choose to solely instruction-tune the backbone with mixed-source data; (3) we discuss how to better utilize extended context windows and propose hybrid-resolution training. Built on the Qwen-VL series model, we propose Giraffe, which is effectively extended to 128K lengths. Evaluated on extensive long context VLM benchmarks such as VideoMME and Viusal Haystacks, our Giraffe achieves state-of-the-art performance among similarly sized open-source long VLMs and is competitive with commercial model GPT-4V. We will open-source the code, data, and models.

Design Choices for Extending the Context Length of Visual Language Models

Long-context language models (LCLMs) have exhibited impressive capabilities in long-context understanding tasks. Among these, long-context referencing—a crucial task that requires LCLMs to attribute items of interest to specific parts of long-context data—remains underexplored. To bridge this gap, this paper proposes Referencing Evaluation for Long-context Language Models (Ref-Long), a novel benchmark designed to assess the long-context referencing capability of LCLMs. Specifically, Ref-Long requires LCLMs to identify the indexes of documents that reference a specific key, emphasizing contextual relationships between the key and the documents over simple retrieval. Based on the task design, we construct three subsets ranging from synthetic to realistic scenarios to form the Ref-Long benchmark. Experimental results of 13 LCLMs reveal significant shortcomings in long-context referencing, even among advanced models like GPT-4o. To further investigate these challenges, we conduct comprehensive analyses, including human evaluations, task format adjustments, fine-tuning experiments, and error analyses, leading to several key insights. Our data and code will be publicly released, and the data is also attached in the submission.

Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models

Linguistic coordination—a phenomenon where conversation partners end up having similar patterns of language use—has been established across a variety of contexts and for multiple linguistic features. However, the study of language coordination has been accompanied by a diverse and inconsistently applied set of measures and theoretical perspectives. This diversity has significant consequences, as replication studies have highlighted the brittleness of certain measures and called influential findings into question. While prior work has addressed specific modeling decisions and model types, linguistic coordination research has yet to fully examine, synthesize, and critique the space of modeling choices available. In this work, we present a framework to organize the linguistic coordination literature. Using this schema, we provide a high-level overview of the choices involved in the measurement process and synthesize relevant critiques. Based on both gaps and limitations surfaced from this review, we suggest directions for further exploration and evaluation. In doing so, we provide the clarity required for linguistic coordination research to arrive at interpretable and sound conclusions.

Coordinating Chaos: A Structured Review of Linguistic Coordination Methodologies

While Transformer models have achieved remarkable success in various domains, the effectiveness of information propagation through deep networks remains a critical challenge. Standard hidden state residuals often fail to adequately preserve initial token-level information in deeper layers. This paper introduces ResFormer, a novel architecture that enhances information flow by incorporating value residual connections in addition to hidden state residuals. And a variant is SVFormer, where all layers share the first layer's value embedding. Comprehensive empirical evidence demonstrates ResFormer achieves equivalent validation loss with 16.11\% fewer model parameters and 20.3\% less training data compared to Transformer, while maintaining similar memory usage and computational cost. Besides, SVFormer reduces KV cache size by nearly half with only a small performance penalty and can be integrated with other KV-efficient methods, yielding further reductions in KV cache, with performance influenced by sequence length and cumulative learning rate.

Value Residual Learning

Large Language Model (LLM) Uncertainty Estimation (UE) methods have become a crucial tool for detecting hallucinations in recent years. While numerous UE methods have been proposed, most existing studies evaluate them in isolated short-form QA settings using threshold-independent metrics such as AUROC or PRR. However, real-world deployment of UE methods introduces several challenges. In this work, we systematically examine four key aspects of deploying UE methods in practical settings. Specifically, we assess (1) the sensitivity of UE methods to decision threshold selection, (2) their robustness to query transformations such as typos, adversarial prompts, and prior chat history, (3) their applicability to long-form generation, and (4) strategies for handling multiple UE scores for a single query. Our evaluations on 19 UE methods reveal that most of them are highly sensitive to threshold selection when there is a distribution shift in the calibration dataset. While these methods generally exhibit robustness against previous chat history and typos, they are significantly vulnerable to adversarial prompts. Additionally, while existing UE methods can be adapted for long-form generation through various strategies, there remains considerable room for improvement. Lastly, ensembling multiple UE scores at test time provides a notable performance boost, which highlights its potential as a practical improvement strategy. Code is available at: https://github.com/duygunuryldz/uncertainty_in_the_wild.

Reconsidering LLM Uncertainty Estimation Methods in the Wild

LLMs exhibit promising Social Intelligence (SI) in modeling human behavior, raising the need to evaluate LLMs' SI and their discrepancy with humans. SI equips humans with interpersonal abilities to behave wisely in navigating social interactions to achieve social goals. This presents an operational evaluation paradigm: outcome-oriented goal achievement evaluation and process-oriented interpersonal ability evaluation, which existing work fails to address. To this end, we propose SocialEval, a script-based bilingual SI benchmark, integrating outcome- and process-oriented evaluation by manually crafting narrative scripts. Each script is structured as a world tree that contains plot lines driven by interpersonal ability, providing a comprehensive view of how LLMs navigate social interactions. Experiments show that LLMs fall behind humans on both SI evaluations, exhibit prosociality, and prefer more positive social behaviors, even if they lead to goal failure. Analysis of LLMs' formed representation space and neuronal activations reveals that LLMs have developed ability-specific functional partitions akin to the human brain.

SocialEval: Evaluating Social Intelligence of Large Language Models

Controlling the output of Large Language Models (LLMs) through context-sensitive constraints has emerged as a promising approach to overcome the limitations of Context-Free Grammars (CFGs) in guaranteeing generation validity. However, such constraints typically require manual specification---a significant barrier demanding specialized expertise. We introduce a framework that automatically learns context-sensitive constraints from LLM interactions through a two-phase process: syntactic exploration to gather diverse outputs for constraint learning, followed by constraint exploitation to enforce these learned rules during generation. Experiments demonstrate that our method enables even small LLMs (1B parameters) to learn and generate with perfect constraint adherence, outperforming larger counterparts and state-of-the-art reasoning models. This work represents the first integration of context-sensitive grammar learning with LLM generation, eliminating manual specification while maintaining generation validity.

Learning and Enforcing Context-Sensitive Control for LLMs

The success of Transformer-based language models in NLP has sparked debate about their ability to simulate human language learning. Chomsky contends that these models indiscriminately acquire both natural and "impossible" languages. While recent studies have challenged this claim, the capacity of Transformers to handle unconventional linguistic structures remains underexplored.
Inspired by natural and speculative languages with circular structural properties, this study examines the ability of GPT-2 to learn languages featuring circular schemes. We synthesize such circular languages by mapping original sequences onto textual circles and then relinearize them using parametric, mathematically invertible procedures that "unwrap" the circles into linear sequences.
We train GPT-2 models on these relinearized corpora and assess the impact of linearization parameters by tracking structural distortion and measuring perplexity. Interestingly, high levels of distortion relative to the original structures do not necessarily correspond to increased perplexity, suggesting that GPT-2 is relatively insensitive to global token order during language acquisition. Instead, preserving local context during linearization plays a more critical role in model learning. Further analysis using surprisal differences reveals that positional shifts pose greater challenges to the model than changes in stride or direction, underscoring the nuanced effects of linearization strategies. These findings offer new insights into the inductive biases of Transformer-based models in acquiring unconventional linguistic structures.

Downloads

Next from ACL 2025

Scalable Vision Language Model Training via High Quality Data Curation

Similar lecture

Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP