United States

As large language models (LLMs) become increasingly integrated into daily applications, it is essential to ensure they function fairly across diverse user demographics. In this work, we show that LLMs suffer from personalization bias, where their performance is impacted when they are personalized to a user&#39;s identity. We quantify personalization bias by evaluating the performance of LLMs along two axes - safety and utility. We measure safety by examining how benign LLM responses are to unsafe prompts. We measure utility by evaluating the LLM&#39;s performance on various tasks, including general knowledge, mathematical abilities, programming, and reasoning skills. We find that various LLMs, ranging from open-source models like Llama-3.1 and Mistral to API-based ones like GPT-3.5 and GPT-4o, exhibit significant variance in performance in terms of safety and utility when personalized with different user identities. Finally, we discuss several strategies to mitigate personalization bias and investigate the origin of personalization bias.

NAACL 2025

Exploring Safety-Utility Trade-Offs in Personalized Language Models

safety

personalization

bias

### 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**. 

ACL 2025

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

As large language models (LLMs) become increasingly integrated into daily applications, it is essential to ensure they function fairly across diverse user demographics. In this work, we show that LLMs suffer from personalization bias, where their performance is impacted when they are personalized to a user's identity. We quantify personalization bias by evaluating the performance of LLMs along two axes - safety and utility. We measure safety by examining how benign LLM responses are to unsafe prompts. We measure utility by evaluating the LLM's performance on various tasks, including general knowledge, mathematical abilities, programming, and reasoning skills. We find that various LLMs, ranging from open-source models like Llama-3.1 and Mistral to API-based ones like GPT-3.5 and GPT-4o, exhibit significant variance in performance in terms of safety and utility when personalized with different user identities. Finally, we discuss several strategies to mitigate personalization bias and investigate the origin of personalization bias.

technical paper

### 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

In an effort to mitigate the harms of large language models (LLMs), learning from human feedback (LHF) has been used to steer LLMs towards outputs that are intended to be both less harmful and more helpful. Despite the widespread adoption of LHF in practice, the quality of this feedback and its effectiveness as a safety mitigation technique remain unclear. This study addresses these issues by auditing the widely-used Helpful and Harmless (HH) dataset by Anthropic. Our work includes: (1) a thorough investigation of the dataset's content through both manual and automated evaluation; (2) experiments demonstrating the dataset's impact on models' safety; and (3) an analysis of the 100 most influential papers citing this dataset. Through our audit, we showcase how conceptualization failures and quality issues identified in the HH dataset can create additional harms by leading to disparate safety behaviors across demographic groups. Our findings highlight the need for more nuanced, context-sensitive approaches to safety mitigation in LLMs.

Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset

Autonomous agents powered by large language models (LLMs) have attracted significant research interest. However, the open-source community faces many challenges in developing specialized models for agent tasks, driven by the scarcity of high-quality agent datasets and the absence of standard protocols in this area. We introduce xLAM, a series of large action models designed for AI agent tasks. The xLAM series includes five models with both dense and mixture-of-expert architectures, ranging from 1B to 8x22B parameters, trained using a scalable, flexible pipeline that unifies, augments, and synthesizes diverse datasets to enhance AI agents' generalizability and performance across varied environments. Our experimental results demonstrate that xLAM consistently delivers exceptional performance across multiple agent ability benchmarks, notably securing the 1st position on the Berkeley Function-Calling Leaderboard, outperforming GPT-4, Claude-3, and many other models in terms of tool use. By releasing the xLAM series, we aim to advance the performance of open-source LLMs for autonomous AI agents, potentially accelerating progress and democratizing access to high-performance models for agent tasks.

xLAM: A Family of Large Action Models to Empower AI Agent Systems

Large language models (LLMs) have shown the emergent capability of in-context learning (ICL). One line of research has claimed that ICL is functionally equivalent to gradient descent, a type of error-driven learning mechanism. In this paper, we introduce a new way of diagnosing whether ICL is functionally performing error-driven learning. Our approach is based on the inverse frequency effect (IFE)---a phenomenon in which an agent's behavior is influenced to a greater degree when presented with improbable examples as compared to more likely ones. The IFE has previously been identified in psycholinguistics where humans exhibit the IFE in the context of structural priming (the tendency for people to produce sentence structures they have encountered recently). In that context, the IFE has been used as evidence that human structural priming must involve error-driven learning mechanisms. In our experiments, we simulated structural priming with ICL and found that LLMs indeed display the IFE, with the effect being stronger in larger models. We conclude that at least in the case we studied, ICL is indeed a type of error-driven learning, supporting the hypothesis that an error signal is implicitly computed in the forward pass during ICL. Our results suggest that both humans and LLMs make use of error-driven processing mechanisms in on-line processing.

Is In-Context Learning a Type of Error-Driven Learning? Evidence from the Inverse Frequency Effect in Structural Priming

Automated construction of shopping cart from
medical prescriptions is a vital prerequisite for
scaling up online pharmaceutical services
in emerging markets due to the high prevalence of paper prescriptions
that are challenging for customers to interpret.
We present RxLens, a multi-step end-end Large Language Model (LLM)-based deployed solution
for automated pharmacy cart construction comprising
multiple steps: redaction of Personal Identifiable Information (PII),
Optical Character Recognition (OCR), medication extraction, matching against the catalog, and bounding box detection for lineage. Our multi-step design leverages the synergy between retrieval and LLM-based generation
to mitigate the vocabulary gaps in LLMs and fuzzy matching errors during retrieval.
Empirical evaluation demonstrates that RxLens can yield up to 19% - 40% and 11% - 26% increase in Recall@3 relative to SOTA methods such as Medical Comprehend and vanilla retrieval augmentation of LLMs on handwritten and printed prescriptions respectively.
We also explore LLM-based auto-evaluation as an alternative to costly manual annotations and observe a 76% - 100% match relative to human judgements on various tasks.

RxLens: Multi-Agent LLM-powered Scan and Order for Pharmacy

Evaluating Large Language Models (LLMs) in low-resource and linguistically diverse languages remains a significant challenge in NLP, particularly for languages using non-Latin scripts like those spoken in India. Existing benchmarks predominantly focus on English, leaving substantial gaps in assessing LLM capabilities in these languages. We introduce MILU, a Multi-task Indic Language Understanding Benchmark, a comprehensive evaluation benchmark designed to address this gap. MILU spans 8 domains and 41 subjects across 11 Indic languages, reflecting general and culturally specific knowledge. With an India-centric design, incorporates material from regional and state-level examinations, covering topics such as local history, arts, festivals, and laws, alongside standard subjects like science and mathematics. We evaluate over 42 LLMs, and find that current LLMs struggle with MILU, with GPT-4o achieving the highest average accuracy at 74 percent. Open multilingual models outperform language-specific fine-tuned models, which perform only slightly better than random baselines. Models also perform better in high resource languages as compared to low resource ones. Domain-wise analysis indicates that models perform poorly in culturally relevant areas like Arts and Humanities, Law and Governance compared to general fields like STEM. To the best of our knowledge, MILU is the first of its kind benchmark focused on Indic languages, serving as a crucial step towards comprehensive cultural evaluation. All code, benchmarks, and artifacts are publicly available to foster open research.

MILU: A Multi-task Indic Language Understanding Benchmark

The rise of generative chat-based Large Language Models (LLMs) over the past two years has spurred a race to develop systems that promise near-human conversational and reasoning experiences. However, recent studies indicate that the language understanding offered by these models remains limited and far from human-like performance, particularly in grasping the contextual meanings of words—an essential aspect of reasoning. In this paper, we present a simple yet computationally efficient framework for multilingual Word Sense Disambiguation (WSD). Our approach reframes the WSD task as a cluster discrimination analysis over a semantic network refined from BabelNet using group algebra. We validate our methodology across multiple WSD benchmarks, achieving a new state of the art for all languages and tasks, as well as in individual assessments by part of speech. Notably, our model significantly surpasses the performance of current alternatives, even in low-resource languages, while reducing the parameter count by 72%.

SANDWiCH: Semantical Analysis of Neighbours for Disambiguating Words in Context ad Hoc

While compositional accounts of human language understanding are based on a hierarchical tree-like process, neural models like transformers lack a direct inductive bias for such tree structures. Introducing syntactic inductive biases could unlock more robust and data-efficient learning in transformer language models (LMs), but existing methods for incorporating such structure greatly restrict models, either limiting their expressivity or increasing inference complexity. This work instead aims to softly inject syntactic inductive biases into given transformer circuits, through a structured regularizer. We introduce TreeReg, an auxiliary loss function that converts bracketing decisions from silver parses into a set of differentiable orthogonality constraints on vector hidden states. TreeReg integrates seamlessly with the standard LM objective, requiring no architectural changes. LMs pre-trained with TreeReg on natural language corpora such as WikiText-103 achieve up to 10% lower perplexities on out-of-distribution data and up to 9.5 point improvements in syntactic generalization, requiring less than half the training data to outperform standard LMs. TreeReg still provides gains for pre-trained LLMs: Continued pre-training of Sheared Llama with TreeReg results in improved syntactic generalization, and fine-tuning on MultiNLI with TreeReg mitigates degradation of performance on adversarial NLI benchmarks by 41.2 points. We release all code to guide future research.

Sneaking Syntax into Transformer Language Models with Tree Regularization

Language models (LMs) are increasingly used as simulacra for people, yet their ability to match the distribution of views of a specific demographic group and be *distributionally aligned* remains uncertain. This notion of distributional alignment is complex, as there is significant variation in the types of attributes that are simulated. Prior works have underexplored the role of three critical variables---the question domain, steering method, and distribution expression method---which motivates our contribution of a benchmark explicitly addressing these dimensions. We construct a dataset expanding beyond political values, create human baselines for this task, and evaluate the extent to which an LM can align with a particular group's opinion distribution to inform design choices of such simulation systems. Our analysis reveals open problems regarding if, and how, LMs can be used to simulate humans, and that LLMs can more accurately describe the opinion distribution than simulate such distributions.

Benchmarking Distributional Alignment of Large Language Models

Knowledge graph embeddings (KGE) apply machine learning methods on knowledge graphs (KGs) to provide non-classical reasoning capabilities based on similarities and analogies. The learned KG embeddings are typically used to answer queries by ranking all potential answers, but rankings often lack a meaningful probabilistic interpretation - lower-ranked answers do not necessarily have a lower probability of being true. This limitation makes it difficult to quantify uncertainty of model's predictions, posing challenges for the application of KGE methods in high-stakes domains like medicine. We address this issue by applying the theory of conformal prediction that allows generating answer sets, which contain the correct answer with probabilistic guarantees. We explain how conformal prediction can be used to generate such answer sets for link prediction tasks. Our empirical evaluation on four benchmark datasets using six representative KGE methods validates that the generated answer sets satisfy the probabilistic guarantees given by the theory of conformal prediction. We also demonstrate that the generated answer sets often have a sensible size and that the size adapts well with respect to the difficulty of the query.

Conformalized Answer Set Prediction for Knowledge Graph Embedding

Event Argument Extraction (EAE) is a key task in natural language processing, focusing on identifying and classifying event arguments in text. However, the widely adopted exact span match (ESM) evaluation metric has notable limitations due to its rigid span constraints, often misidentifying valid predictions as errors and underestimating system performance. In this paper, we evaluate nine state-of-the-art EAE models on the RAMS and GENEVA datasets, highlighting ESM's limitations. To address these issues, we introduce BEMEAE (Beyond Exact Span Match for Event Argument Extraction), a novel evaluation metric that recognizes predictions that are semantically equivalent to or improve upon the reference. BEMEAE integrates deterministic components with a semantic matching component for more accurate assessment. Our experiments demonstrate that BEMEAE aligns more closely with human judgments. We show that BEMEAE not only leads to higher F1 scores compared to ESM but also results in significant changes in model rankings, underscoring ESM's inadequacy for comprehensive evaluation of EAE.

Downloads

Next from NAACL 2025

Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset

Similar lecture

LLMs + Persona-Plug = Personalized LLMs