India

In this work, we introduce PII-Scope, a comprehensive benchmark designed to evaluate state-of-the-art methodologies for PII extraction attacks targeting LLMs across diverse threat settings. Our study provides a deeper understanding of these attacks by uncovering several hyperparameters (e.g., demonstration selection) crucial to their effectiveness. Building on this understanding, we extend our study to more realistic attack scenarios, exploring PII attacks that employ advanced adversarial strategies, including repeated and diverse querying, and leveraging iterative learning for continual PII extraction. Through extensive experimentation, our results reveal a notable underestimation of PII leakage in existing single-query attacks. In fact, we show that with sophisticated adversarial capabilities and a limited query budget, PII extraction rates can increase by up to fivefold when targeting the pretrained model. Moreover, we evaluate PII leakage on finetuned models, showing that they are more vulnerable to leakage than pretrained models. Overall, our work establishes a rigorous empirical benchmark for PII extraction attacks in realistic threat scenarios and provides a strong foundation for developing effective mitigation strategies.

IJCNLP-AACL 2025

PII-Scope: A Comprehensive Study on Training Data Privacy Leakage in Pretrained LLMs

llm memorization

pii attack

privacy leakage

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

ACL 2026

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

poster

### Welcome to IJCNLP-AACL 2025! 
 It is a great honor to host this joint conference in Mumbai, India, from December 20 to 24, 2025. The joint conferences of IJCNLP and AACL are organized with alternating leadership in the Asia-Pacific region. The event is run by the Asian Federation of Natural Language Processing (AFNLP) in odd years, and by AACL in even years, while it is organized solely by ACL when the annual ACL meeting is held in the region. This year, the conference is primarily organized by AFNLP. 
*Kentaro Inui
MBZUAI, UAE
General Chair, IJCNLP-AACL 2025* 
Read full message and download the Conference Handbook [**here**](https://drive.google.com/file/d/1UTwxkAqSqI-GAoJC3wE1zZt5VP1Y8GX0/view?usp=sharing).

The 14th IJCNLP & 4th AACL will be held in Mumbai, India from December 20th to December 24th, 2025.

Uniform Meaning Representation (UMR) is a recently developed graph-based semantic representation, which expands on Abstract Meaning Representation (AMR) in a number of ways, in particular through the inclusion of document-level information and multilingual flexibility. In order to effectively adopt and leverage UMR for downstream tasks, efforts must be placed toward developing a UMR technological ecosystem. Though only a small amount of UMR annotations have been produced to date, in this work, we investigate the first approaches to producing text from multilingual UMR graphs. Exploiting the structural similarity between UMR and AMR graphs and the wide availability of AMR technologies, we introduce (1) a baseline approach which passes UMR graphs to AMR-to-text generation models, (2) a pipeline conversion of UMR to AMR, then using AMR-to-text generation models, and (3) a fine-tuning approach for both foundation models and AMR-to-text generation models with UMR data. Our best performing models achieve multilingual BERTscores of 0.825 for English and 0.882 for Chinese, a promising indication of the effectiveness of fine-tuning approaches for UMR-to-text generation even with limited UMR data.

Generating Text from Uniform Meaning Representation

Contextual entropy is a psycholinguistic measure capturing the anticipated difficulty of processing a word just before it is encountered. Recent studies have tested for entropy-related effects as a potential complement to well-known effects from surprisal. For convenience, entropy is typically estimated based on a language model’s probability distribution over a word’s first subword token. However, this approximation results in underestimation and potential distortion of true word entropy. To address this, we generate Monte Carlo (MC) estimates of word entropy that allow words to span a variable number of tokens. Regression experiments on reading times show divergent results between first-token and MC word entropy, suggesting a need for caution in using first-token approximations of contextual entropy.

How Well Does First-Token Entropy Approximate Word Entropy as a Psycholinguistic Predictor?

We tested over 20 Transformer models for ranking long documents (including recent LongP models trained with FlashAttention and RankGPT models "powered" by OpenAI and Anthropic cloud APIs).
We compared them with the simple FirstP baseline, which applied the same model to truncated input (up to 512 tokens).
On MS MARCO, TREC DL, and Robust04 no long-document model outperformed FirstP by more than 5% (on average).
We hypothesized that this lack of improvement is not due to inherent model limitations,
but due to benchmark positional bias (most relevant passages tend to occur early in documents),
which is known to exist in MS MARCO.
To confirm this, we analyzed positional relevance distributions across four long-document corpora (with six query sets) and observed the same early-position bias.
Surprisingly, we also found bias in six BEIR collections, which are typically categorized as
short-document datasets.
We then introduced a new diagnostic dataset, MS MARCO FarRelevant, where relevant spans were deliberately placed beyond the first 512 tokens.
On this dataset, many long-context models–-including RankGPT–-performed at random-baseline level, suggesting overfitting to positional bias.
We also experimented with debiasing training data, but with limited success.
Our findings (1) highlight the need for careful benchmark design in evaluating long-context models for document ranking, (2) identify model types that are more robust to positional bias, and (3) motivate further work on approaches to debias training data.
We release our code and data to support further research.

Positional Bias in Long-Document Ranking: Impact, Assessment, and Mitigation

Document retrieval is a critical challenge in information retrieval systems, where the goal is to efficiently retrieve relevant documents in response to a given query. Dense retrieval methods, which utilize vector embeddings to represent semantic information, require effective indexing to ensure fast and accurate retrieval. Existing methods, such as MEVI, have attempted to address this by using hierarchical K-Means for clustering, but they often face limitations in computational efficiency and retrieval accuracy. In this paper, we introduce the Hildoc Index, a novel document indexing approach that leverages the Hilbert Curve to map document embeddings onto a one-dimensional space. This innovative representation facilitates efficient clustering using a 1D quantile-based algorithm, ensuring uniform partition sizes and preserving the inherent structure of the data. As a result, Hildoc Index not only reduces training complexity but also enhances retrieval accuracy and speed during inference. Our method can be seamlessly integrated into both dense retrieval systems and hybrid ensemble systems. Through comprehensive experiments on standard benchmarks like MSMARCO Passage and Natural Questions, we demonstrate that the Hildoc Index significantly outperforms the current state-of-the-art MEVI in terms of both retrieval speed and recall. These results underscore the Hildoc Index as a solution for fast and accurate dense document retrieval.

Hildoc: Leveraging Hilbert Curve Representation for Accurate and Efficient Document Retrieval

Decomposing sentences into fine-grained meaning units is increasingly used to model semantic alignment. While QA-based semantic approaches have shown effectiveness for representing predicate-argument relations, they have so far left noun-centered semantics largely unaddressed. We introduce QA-Noun, a QA-based framework for capturing noun-centered semantic relations. QA-Noun defines nine question templates that cover both explicit syntactical and implicit contextual roles for nouns, producing interpretable QA pairs that complement verbal QA-SRL. We release detailed guidelines, a dataset of over 2,000 annotated noun mentions, and a trained model integrated with QA-SRL to yield a unified decomposition of sentence meaning into individual, highly fine-grained, facts. Evaluation shows that QA-Noun achieves near-complete coverage of AMR's noun arguments while surfacing additional contextually implied relations, and that combining QA-Noun with QA-SRL yields over 130% higher granularity than recent fact-based decomposition methods such as FactScore and DecompScore. QA-Noun thus complements the broader QA-based semantic framework, forming a comprehensive and scalable approach to fine-grained semantic decomposition for cross-text alignment.

QA-Noun: Representing Nominal Semantics via Natural Language Question-Answer Pairs

Model compression has emerged as a mainstream solution to reduce memory usage and computational overhead. This paper proposes GQSA, a novel model compression framework specifically designed for LLMs. Traditional methods typically focus exclusively on either quantization or sparsification, but relying on a single strategy often results in significant performance loss at high compression rates. In contrast, GQSA integrates quantization and sparsification in a tightly coupled manner, leveraging GPU-friendly structured group sparsity and quantization for efficient acceleration. Building upon system-algorithm co-design principles, we propose a two-stage sparse optimization strategy that ensures the performance superiority of the compressed model. On the engine side, we introduce a "task-centric" parallel strategy, which, to the best of our knowledge, is the first application in the domain of sparse computing. Compared to the traditional 2:4 sparse method, the GQSA offers a more flexible and adjustable sparsity rate, as well as a higher weight compression rate, and is efficiently compatible with weight-only quantization methods. Experimental results demonstrate that, under the GQSA W4S50% compression setting, the model’s accuracy surpasses that of both 2:4 pruning and W2 quantization. Furthermore, at the inference level, GQSA outperforms W2 by 1.26 $\times$ and 2:4 pruning by 2.35 $\times$ in terms of speed.

GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference

Certain strong LLMs have shown promise for zero-shot formal planning by generating planning languages like PDDL. Yet, performance of most open-source models under 50B parameters has been reported to be close to zero due to the low-resource nature of these languages. We significantly improve their performance via a series of lightweight pipelines that integrates documentation retrieval with modular code generation and error refinement. With models like Llama-4-Maverick, our best pipeline improves plan correctness from 0\% to over 80\% on the common BlocksWorld domain. However, while syntactic errors are substantially reduced, semantic errors persist in more challenging domains, revealing fundamental limitations in current models' reasoning capabilities.

Documentation Retrieval Improves Planning Language Generation

We systematically investigate cross-lingual ability transfer in language models through controlled experiments across three problem sets: algorithmic addition, graph navigation, and natural language modeling. Our experimental design creates high-resource and low-resource "language" pairs differing in vocabulary, grammar, and computational requirements. We show that training on mixed datasets consistently enables strong positive transfer, significantly improving low-resource language performance compared to training on low amount of data in isolation. We observe improvements from 0% to 100% accuracy in arithmetic tasks, from 24% to 98% accuracy in graph navigation tasks, and 69.6% perplexity reduction in natural language modeling. We demonstrate that transfer effectiveness depends on computational complexity and linguistic differences, where grammar modifications support stronger transfer than vocabulary modifications. These findings provide compelling evidence that cross-lingual ability transfer is a robust mechanism which contributes to the quality of large language models in low-resource languages.

Ability Transfer Through Language Mixing

Large Language Models (LLMs) often produce factoid hallucinations - plausible yet incorrect answers. A common mitigation strategy is model alignment, which improves factual accuracy by training on curated (factual, non-factual) pairs. However, this approach often relies on a stronger model (e.g., GPT-4) or an external knowledge base to assess factual correctness that may not always be accessible. Addressing this, we propose Atomic Consistency Preference Optimization (ACPO), a self-supervised preference-tuning method that enhances factual accuracy without external supervision. ACPO leverages atomic consistency signals (i.e., the agreement of individual facts across multiple stochastic responses) to identify high- and low-quality data pairs for model alignment. Despite being fully self-supervised, ACPO outperforms the strong supervised alignment baseline by $1.95$ points averaged across Phi-3 and Llama3 on the LongFact and BioGen datasets, demonstrating its effectiveness in improving factual reliability without relying on external models or knowledge bases.

Atomic Consistency Preference Optimization for Long-Form Question Answering

Large language models (LLMs) achieve good performance on challenging reasoning benchmarks, yet could also make basic reasoning mistakes. This contrasting behavior is puzzling when it comes to understanding the mechanisms behind LLMs' reasoning capabilities. One hypothesis is that the increasingly high and nearly saturated performance on common reasoning benchmarks could be due to the memorization of similar problems. In this paper, we systematically investigate this hypothesis with a quantitative measurement of memorization in reasoning tasks, using two dynamically generated logical reasoning benchmarks based on Knights and Knaves (K&K) puzzles and Zebra puzzles (DynamicZebra). We find that LLMs could interpolate and memorize the training puzzles (achieving near-perfect accuracy) after fine-tuning, yet they struggle with slight variations of these puzzles. On the other hand, we show that while fine-tuning leads to heavy memorization, it also consistently improves generalization performance. Through in-depth analyses with perturbation tests, cross difficulty-level transferability, probing model internals, and fine-tuning with wrong answers, we establish that LLMs develop reasoning skills on logical puzzles alongside memorization. Finally, our analysis based on a per-sample memorization score sheds light on how LLMs switch between reasoning and memorization when solving logical puzzles.

Downloads

Next from IJCNLP-AACL 2025

Generating Text from Uniform Meaning Representation

Similar lecture

PII-Bench: Evaluating Query-Aware Privacy Protection Systems