United States

Understanding and mitigating the potential risks associated with foundation models (FMs) hinges on developing effective interpretability methods. Sparse Autoencoders (SAEs) have emerged as a promising tool for disentangling FM representations, but they struggle to capture rare, yet crucial concepts in the data. We introduce Specialized Sparse Autoencoders (SSAEs), designed to illuminate these elusive dark matter features by focusing on specific subdomains. We present a practical recipe for training SSAEs, demonstrating the efficacy of dense retrieval for data selection and the benefits of Tilted Empirical Risk Minimization as a training objective to improve concept recall. Our evaluation of SSAEs on standard metrics, such as downstream perplexity and $L_0$ sparsity, show that they effectively capture subdomain tail concepts, exceeding the capabilities of general-purpose SAEs. We showcase the practical utility of SSAEs in a case study on the Bias in Bios dataset, where SSAEs achieve a 12.5% increase in worst-group classification accuracy over the pretrained general-purpose SAE when applied to remove spurious gender information. SSAEs provide a powerful new lens for peering into the inner workings of FMs in subdomains.

NAACL 2025

Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models

hierarchical & concept explanations

free-text/natural language explanations

feature attribution

probing

poster

### Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Large Language Models (LLMs) have showcased their potential in building generative recommendation systems through fine-tuning user behavior data. However, utilizing the user behavior data may pose significant privacy risks like in the traditional recommender models, potentially leading to ethical dilemmas and violations of data protection regulations. To address the privacy concerns, Federated Learning for Recommendation (Fed4Rec) has been identified as a promising solution. However, directly applying Fed4Rec in the LLM context introduces two challenges: 1) exacerbated client performance imbalance, which ultimately impacts the system's long-term effectiveness, and 2) substantial client resource costs, posing a high demand for clients' both computational and storage capability to locally train and infer LLMs. To tackle these challenges, we propose a federated framework for LLM-based recommendation (shorted as FELLRec). Generally, FELLRec designs two key strategies. 1) Dynamic balance strategy, which designs dynamic parameter aggregation and learning speed for different clients during training, aiming to ensure relatively balanced performance across clients. 2) Flexible storage strategy, which selectively retains certain sensitive LLM layers on the client side, while offloading other layers to the server, aiming to preserve privacy while saving resources. Specifically, FELLRec flexibly maintains those input and output layers on the client side to ensure the protection of all sensitive information. Experiment results show that FELLRec can achieve a more balanced client performance and improved overall performance in a computational and storage-efficient way while safeguarding user privacy well.

A Federated Framework for LLM-based Recommendation

Medical-specific Large Language Models (LLMs) have demonstrated impressive performance on medical-related exams and tasks. Despite their success in single-turn question and answering, instruction-tuned LLMs often falter in real-world healthcare applications, highlighting a disconnect between existing instruction datasets and practical contexts. To address this issue, we propose Service Flow aware Medical Scenario Simulation (SFMSS), a simulation framework designed for medical conversational data generation. SFMSS employs three key strategies to ensure the quality of the data generation. the use of Authentic Seed Data ensures alignment of real-world distributions. Diverse Patient Simulation enables simulated patients to exhibit distinct communication styles and complex behavioral logic. Service Flow Control ensures that conversations progress in alignment with medical objectives. We construct a dataset targeting on outpatient reception through SFMSS, named SFMSS-CD. Building on this dataset, we develop a model called SFMSS-Nurse. We conduct both automatic and human evaluations, involving 15 users and 15 clinical experts, to assess the effectiveness of SFMSS. The results demonstrate that SFMSS-Nurse outperforms all baselines, including the current state-of-the-art model GPT-4o, and aligns with human preferences and clinical demands.

SFMSS: Service Flow aware Medical Scenario Simulation for Conversational Data Generation

Recent advancements in AI for biological research focus on integrating molecular data with natural language to accelerate drug discovery. However, the scarcity of high-quality annotations limits progress in this area. This paper introduces LA3, a Language-based Automatic Annotation Augmentation framework that leverages large language models to augment existing datasets, thereby improving AI training. We demonstrate the effectiveness of LA3 by creating an enhanced dataset, LaChEBI-20, where we systematically rewrite the annotations of molecules from an established dataset. These rewritten annotations preserve essential molecular information while providing more varied sentence structures and vocabulary. Using LaChEBI-20, we train LaMolT5 based on a benchmark architecture to learn the mapping between molecular representations and augmented annotations. Experimental results on text-based *de novo* molecule generation and molecule captioning demonstrate that LaMolT5 outperforms state-of-the-art models. Notably, incorporatingLA3 leads to improvements of up to 301% over the benchmark architecture. Furthermore, we validate the effectiveness of LA3 notable applications in *image*, *text* and *graph* tasks, affirming its versatility and utility.

Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language

The widespread applications of large language models (LLMs) have brought about concerns regarding their potential misuse. Although aligned with human preference data before release, LLMs remain vulnerable to various malicious attacks. In this paper, we adopt a red-teaming strategy to enhance LLM safety and introduce SeqAR, a simple yet effective framework to design jailbreak prompts automatically. The SeqAR framework generates and optimizes multiple jailbreak characters and then applies sequential jailbreak characters in a single query to bypass the guardrails of the target LLM. Different from previous work which relies on proprietary LLMs or seed jailbreak templates crafted by human expertise, SeqAR can generate and optimize the jailbreak prompt in a cold-start scenario using open-sourced LLMs without any seed jailbreak templates. Experimental results show that SeqAR achieves attack success rates of 88% and 60% in bypassing the safety alignment of GPT-3.5-1106 and GPT-4, respectively. Furthermore, we extensively evaluate the transferability of the generated templates across different LLMs and held-out malicious requests, while also exploring defense strategies against the jailbreak attack designed by SeqAR.

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters

Sign language translation has historically been peripheral to mainstream machine translation research. In order to help converge the fields, we introduce FLEURS-ASL, an extension of the multiway parallel benchmarks FLORES (for text) and FLEURS (for speech) to support their first sign language (as video), American Sign Language, translated by 5 Certified Deaf Interpreters. FLEURS-ASL can be used to evaluate a variety of tasks---primarily sentence- and discourse-level translation---between ASL and 200 other languages as text, or 102 languages as speech. We provide baselines for tasks from ASL to English text using a unified modeling approach that incorporates timestamp tokens and previous text tokens in a 34-second context window, trained on random video clips from YouTube-ASL. This model meets or exceeds the performance of phrase-level baselines while supporting a multitude of new tasks. We also use FLEURS-ASL to show that multimodal frontier models have virtually no understanding of ASL, underscoring the importance of including sign languages in standard evaluation suites.

FLEURS-ASL: Including American Sign Language in Massively Multilingual Multitask Evaluation

Large language models (LLMs) are susceptible to memorizing training data, raising concerns due to the potential extraction of sensitive information. Current methods to measure memorization rates of LLMs, primarily discoverable extraction (Carlini et al., 2022; Kassem et al., 2024), rely on single-sequence greedy sampling, potentially underestimating the true extent of memorization. This paper introduces a probabilistic relaxation of discoverable extraction that quantifies the probability of extracting a target sequence within a set of generated samples, considering various sampling schemes and multiple attempts. This approach addresses the limitations of reporting memorization rates through discoverable extraction by accounting for the probabilistic nature of LLMs and user interaction patterns. Our experiments demonstrate that this probabilistic measure can reveal cases of higher memorization rates compared to rates found through discoverable extraction. We further investigate the impact of different sampling schemes on extractability, providing a more comprehensive and realistic assessment of LLM memorization and its associated risks. Our contributions include a new probabilistic memorization definition, empirical evidence of its effectiveness, and a thorough evaluation across different models, sizes, sampling schemes, and training data repetitions.

A probabilistic measure of memorization for large language models

Zero-shot Named Entity Recognition (ZS-NER) aims to recognize entities in unseen domains without specific annotated data. A key challenge is handling missing entities while ensuring accurate type recognition, hindered by: 1) the pre-training assumption that each entity has a single type, overlooking diversity, and 2) insufficient contextual knowledge for type reasoning. To address this, we propose IRRA (Integrated Recall and Retrieval Augmentation), a novel two-stage framework leveraging large language model techniques. In the \emph{Recall Augmented Entity Extracting} stage, we built a perturbed dataset to induce the model to exhibit missing or erroneous extracted entities. Based on this, we trained an enhanced model to correct these errors. This approach can improve the ZS-NER’s recall rate. In the \emph{Retrieval Augmented Type Correcting} stage, we employ Retrieval-Augmented Generation techniques to locate entity-related unannotated contexts, with the additional contextual information significantly improving the accuracy of type correcting. Extensive evaluations demonstrate the state-of-the-art performance of our IRRA, with significant improvements in zero-shot cross-domain settings validated through both auto-evaluated metrics and analysis. Our implementation will be open-sourced at \url{https://github.com/DMIRLAB-Group/IRRA}.

Handling Missing Entities in Zero-Shot Named Entity Recognition: Integrated Recall and Retrieval Augmentation

As the prevalence of phishing attacks continues to rise, there is an increasing demand for more robust detection technologies. With recent advances in AI, we discuss how to construct a reliable and practical phishing detection system using language models. For this system, we introduce the first large-scale Korean dataset for phishing detection, encompassing six types of phishing attacks. We consider multiple factors for building a real-time detection system for edge devices, such as model size, Speech-To-Text quality, split length, training technique and multi-task learning. We evaluate the model's ability twofold: in-domain, and unseen attack detection performance which is referred to as zero-day performance. Additionally, we demonstrate the importance of accurate comparison groups and evaluation datasets, showing that voice phishing detection performs reasonably well while smishing detection remains challenging. Both the dataset and the trained model will be available upon request.

Towards Reliable and Practical Phishing Detection

Large language models (LLMs) demonstrate significant potential in advancing medical applications, yet their capabilities in addressing medical ethics challenges remain underexplored. This paper introduces MedEthicEval, a novel benchmark designed to systematically evaluate LLMs in the domain of medical ethics. Our framework encompasses two key components: knowledge, assessing the models' grasp of medical ethics principles, and application, focusing on their ability to apply these principles across diverse scenarios. To support this benchmark, we consulted with medical ethics researchers and developed three datasets addressing distinct ethical challenges: blatant violations of medical ethics, priority dilemmas with clear inclinations, and equilibrium dilemmas without obvious resolutions. MedEthicEval serves as a critical tool for understanding LLMs' ethical reasoning in healthcare, paving the way for their responsible and effective use in medical contexts.

MedEthicEval: Evaluating Large Language Models Based on Chinese Medical Ethics

Application of LLMs for complex causal question answering can be stymied by their opacity and propensity for hallucination. Although recent approaches such as Retrieval Augmented Generation and Chain of Thought prompting have improved reliability, we argue current approaches are insufficient and further fail to satisfy key criteria humans use to select and evaluate causal explanations. Inspired by findings from the social sciences, we present an implemented causal QA approach that combines iterative RAG with guidance from a formal model of causation. Our causal model is backed by the Cogent reasoning engine, allowing users to interactively perform counterfactual analysis and refine their answer. Our approach has been integrated into a deployed Collaborative Research Assistant (Cora) and we present an evaluation in the life sciences domain.

Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models

Downloads

Next from NAACL 2025

A Federated Framework for LLM-based Recommendation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES