Austria

The rapid growth of large language models (LLMs) with traditional centralized fine-tuning emerges as a key technique for adapting these models to domain-specific challenges, yielding privacy risks for both model and data owners. One promising solution, called offsite-tuning (OT), is proposed to address these challenges, where a weaker emulator is compressed from the original model and further fine-tuned with adapter to enhance privacy. However, the existing OT-based methods require high computational costs and lack theoretical analysis. This paper introduces a novel OT approach based on gradient-preserving compression. By analyzing the OT problem through the lens of optimization, we propose a method that selectively applies compression techniques such as rank compression and channel pruning, preserving the gradients of fine-tuned adapters while ensuring privacy. Extensive experiments demonstrate that our approach surpasses existing OT methods, both in terms of privacy protection and model performance. Our method provides a theoretical foundation for OT and offers a practical, training-free solution for offsite-tuning of large-scale LLMs.

ACL 2025

GradOT: Training-free Gradient-persevering Offsite-tuning for Large Language Models

privacy-preserving llm

offsite-tuning

model privacy

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

AAAI 2025

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



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)

While parallel sentence mining has been extensively covered for fairly well-resourced languages, pairs involving low-resource languages have received comparatively little attention.
To address this gap, we present Belopsem, a benchmark of new datasets for parallel sentence mining on three language pairs where the source side is low-resource and endangered: Occitan-Spanish, Upper Sorbian-German, and Chuvash-Russian. These combinations also reflect varying linguistic similarity within each pair. We compare three language models in an established parallel sentence mining pipeline and apply two types of improvements to one of them, Glot500. We observe better mining quality overall by both applying alignment post-processing with an unsupervised aligner and using a cluster-based isotropy enhancement technique. These findings are crucial for optimising parallel data extraction for low-resource languages in a realistic way.

Improving Parallel Sentence Mining for Low-Resource and Endangered Languages

Solving complex tasks in a single attempt is challenging for large language models (LLMs). Iterative interaction with the environment and feedback is often required to achieve success, making effective feedback utilization a critical topic. Existing approaches either struggle with length generalization or rely on naive retries without leveraging prior information. In this paper, we introduce FTTT, a novel paradigm that formulates feedback utilization as an optimization problem at test time. Additionally, we propose a learnable test-time optimizer, OpTune, to effectively exploit feedback. Experiments on two LLMs across four reasoning datasets demonstrate that FTTT and OpTune achieve superior scalability and performance.

Learning to Reason from Feedback at Test-Time

Long-context models(LCMs) have witnessed remarkable advancements in recent years, facilitating real-world tasks like long-document QA. The success of LCMs is founded on the hypothesis that the model demonstrates strong $\textbf{fidelity}$, enabling it to respond based on the provided long context rather than relying solely on the intrinsic knowledge acquired during pre-training. Yet, in this paper, we find that open-sourced LCMs are not as faithful as expected. We introduce $\textit{L-CiteEval}$, an out-of-the-box suite that can assess both generation quality and fidelity in long-context understanding tasks. It covers 11 tasks with context lengths ranging from 8K to 48K and a corresponding automatic evaluation pipeline. Evaluation of 11 cutting-edge closed-source and open-source LCMs indicates that, while there are minor differences in their generation, open-source models significantly lag behind closed-source counterparts in terms of fidelity. Furthermore, we analyze the benefits of citation generation for LCMs from both the perspective of explicit model output and the internal attention mechanism.

L-CiteEval: A Suite for Evaluating Fidelity of Long-context Models

As large language models (LLMs) are increasingly used in high-stakes domains, accurately assessing their confidence is crucial. Humans typically express confidence through epistemic markers (e.g., "fairly confident") instead of numerical values. However, it remains unclear whether LLMs consistently use these markers to reflect their intrinsic confidence due to the difficulty of quantifying uncertainty associated with various markers. To address this gap, we first define ***marker confidence*** as the observed accuracy when a model employs an epistemic marker. We evaluate its stability across multiple question-answering datasets in both in-distribution and out-of-distribution settings for open-source and proprietary LLMs. Our results show that while markers generalize well within the same distribution, their confidence is inconsistent in out-of-distribution scenarios. These findings raise significant concerns about the reliability of epistemic markers for confidence estimation, underscoring the need for improved alignment between marker based confidence and actual model uncertainty. Our code is available at https://github.com/HKUST-KnowComp/MarCon.

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

Large Language Models (LLMs) such as ChatGPT demonstrate significant potential in the medical domain and are often evaluated using multiple-choice questions (MCQs) modeled on exams like the USMLE. However, such benchmarks may overestimate true clinical understanding by rewarding pattern recognition and test-taking heuristics. To investigate this, we created a fictional medical benchmark centered on an imaginary organ, the Glianorex, allowing us to separate memorized knowledge from reasoning ability. We generated textbooks and MCQs in English and French using leading LLMs, then evaluated proprietary, open-source, and domain-specific models in a zero-shot setting. Despite the fictional content, models achieved an average score of 64%, while physicians scored only 27%. Fine-tuned medical models outperformed base models in English but not in French. Ablation and interpretability analyses revealed that models frequently relied on shallow cues, test-taking strategies, and hallucinated reasoning to identify the correct choice. These results suggest that standard MCQ-based evaluations may not effectively measure clinical reasoning and highlight the need for more robust, clinically meaningful assessment methods for LLMs.

Pattern Recognition or Medical Knowledge? The Problem with Multiple-Choice Questions in Medicine

Transformers, as the fundamental deep learning architecture, have demonstrated great capability in reasoning. This paper studies the generalizable first-order logical reasoning ability of transformers with their *parameterized* knowledge and how to improve it. Transformers' capability of first-order reasoning is further captured by whether they can conduct first-order logical entailment, which is quantitatively measured by their performance in answering knowledge graph queries. We establish the connections between (1) two types of distribution shifts studied in out-of-distribution generalization and (2) unseen knowledge and query settings discussed in the task of knowledge graph query answering, which makes it possible to characterize the fine-grained generalizability. Results on our comprehensive dataset showed that transformers **outperform** previous methods designed particularly for this task and provided detailed empirical evidence about the impact of the input query syntax, token embedding, and transformer architectures on the reasoning capability of transformers. Interestingly, our results revealed the mismatch of positional encoding and other design choices of transformer architectures in previous practices. Motivated by this, we propose **TEGA**, a logic-aware architecture that significantly improves the performance in generalizable first-order logical entailment.

Enhancing Transformers for Generalizable First-Order Logical Entailment

As large language models (LLMs) become increasingly prevalent, concerns about their reliability, particularly due to hallucinations - factually inaccurate or irrelevant outputs - have grown. Our research investigates the relationship between the uncertainty in training dynamics and the emergence of hallucinations. Using models from the Pythia suite and several hallucination detection metrics, we analyze hallucination trends and identify significant variance during training. To address this, we propose Sensitivity Dropout (SenD), a novel training protocol designed to reduce hallucination variance during training by deterministically dropping embedding indices with significant variability. In addition, we develop an unsupervised hallucination detection metric, Efficient EigenScore (EES), which approximates the traditional EigenScore in 2x speed. This metric is integrated into our training protocol, allowing SenD to be both computationally scalable and effective at reducing hallucination variance. SenD improves test-time reliability of Pythia and Meta's Llama models by up to 17% and enhances factual accuracy in Wikipedia, Medical, Legal, and Coding domains without affecting downstream task performance.

Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training

Concept-based explanations work by mapping complex model computations to human-understandable concepts. Evaluating such explanations is very difficult, as it includes not only the quality of the induced space of possible concepts but also how effectively the chosen concepts are communicated to users. Existing evaluation metrics often focus solely on the former, neglecting the latter.

We introduce an evaluation framework for measuring concept explanations via automated simulatability: a simulator's ability to predict the explained model's outputs based on the provided explanations. This approach accounts for both the concept space and its interpretation in an end-to-end evaluation. Human studies for simulatability are notoriously difficult to enact, particularly at the scale of a wide, comprehensive empirical evaluation (which is the subject of this work). We propose using large language models (LLMs) as simulators to approximate the evaluation and report various analyses to make such approximations reliable. Our method allows for scalable and consistent evaluation across various models and datasets. We report a comprehensive empirical evaluation using this framework and show that LLMs provide consistent rankings of explanation methods. Code available at Anonymous GitHub.

ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability

Automated interpretability pipelines generate natural language descriptions for the concepts represented by features in large language models (LLMs), such as "plants" or "the first word in a sentence". These descriptions are derived using inputs that activate the feature, which may be a dimension or a direction in the model's representation space. However, identifying activating inputs is costly, and the mechanistic role of a feature in model behavior is determined both by how inputs cause a feature to activate and by how feature activation affects outputs. Using steering evaluations, we reveal that current pipelines provide descriptions that fail to capture the causal effect of the feature on outputs. To fix this, we propose efficient, output-centric methods for automatically generating feature descriptions. These methods use the tokens weighted higher after feature stimulation or the highest weight tokens after applying the vocabulary "unembedding" head directly to the feature. Our output-centric descriptions better capture the causal effect of a feature on model outputs than input-centric descriptions, but combining the two leads to the best performance on both input and output evaluations. Lastly, we show that output-centric descriptions can be used to find inputs that activate features previously thought to be "dead".

Enhancing Automated Interpretability with Output-Centric Feature Descriptions

Generative models such as Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) trained on massive datasets can lead them to memorize and inadvertently reveal sensitive information, raising ethical and privacy concerns. While some prior works have explored this issue in the context of LLMs, it presents a unique challenge for MLLMs due to the entangled nature of knowledge across modalities, making comprehensive unlearning more difficult. To address this challenge, we propose Modality Aware Neuron Unlearning (MANU), a novel unlearning framework for MLLMs designed to selectively clip neurons based on their relative importance to the targeted forget data, curated for different modalities. Specifically, MANU consists of two stages: important neuron selection and selective pruning. The first stage identifies and collects the most influential neurons across modalities relative to the targeted forget knowledge, while the second stage is dedicated to pruning those selected neurons. MANU effectively isolates and removes the neurons that contribute most to the forget data within each modality, while preserving the integrity of retained knowledge. Our experiments conducted across various MLLM architectures illustrate that MANU can achieve a more balanced and comprehensive unlearning in each modality without largely affecting the overall model utility.

Downloads

Next from ACL 2025

Improving Parallel Sentence Mining for Low-Resource and Endangered Languages

Similar lecture

ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression