United States

While learning to align Large Language Models (LLMs) with human preferences has shown remarkable success, aligning these models to meet the diverse user preferences presents further challenges in preserving previous knowledge. This paper examines the impact of personalized preference optimization on LLMs, revealing that the extent of knowledge loss varies significantly with preference heterogeneity. Although previous approaches have utilized the KL constraint between the reference model and the policy model, we observe that they fail to maintain general knowledge and alignment when facing personalized preferences. To this end, we introduce Base-Anchored Preference Optimization (BAPO), a simple yet effective approach that utilizes the initial responses of reference model to mitigate forgetting while accommodating personalized alignment. BAPO effectively adapts to diverse user preferences while minimally affecting global knowledge or general alignment. Our experiments demonstrate the efficacy of BAPO in various setups.

EMNLP 2024

BAPO: Base-Anchored Preference Optimization for Personalized Alignment in LLMs

text-to-speech

multi-modal

multi-task

speech recognition

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 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 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.

Hierarchical topic models nowadays tend to capture the relationship between words and topics, often ignoring the role of anchor words that guide text generation. For the first time, we detect and add anchor words to the text generation process in an unsupervised way. Firstly, we adopt a clustering algorithm to adaptively detect anchor words that are highly consistent with every topic, which forms the path of topic $\rightarrow$ anchor word. Secondly, we add the causal path of anchor word $\rightarrow$ word to the popular Variational Auto-Encoder (VAE) framework via implicitly using word co-occurrence graphs. We develop the causal path of topic+anchor word $\rightarrow$ higher-layer topic that aids the expression of topic concepts with anchor words to capture a more semantically tight hierarchical topic structure. Finally, we enhance the model's representation of the anchor words through a novel contrastive learning. After jointly training the aforementioned constraint objectives, we can produce more coherent and diverse topics with a better hierarchical structure. Extensive experiments on three datasets show that our model outperforms state-of-the-art methods.

Unsupervised Hierarchical Topic Modeling via Anchor Word Clustering and Path Guidance

Retrieval-augmented generation (RAG) offers an effective approach for addressing question answering (QA) tasks. However, the imperfections of the retrievers in RAG models often result in the retrieval of irrelevant information, which could introduce noise and degrade the performance, especially when handling multi-hop questions that require multiple steps of reasoning. To enhance the multi-hop reasoning ability of RAG models, we propose TRACE. TRACE constructs knowledge-grounded reasoning chains, which are a series of logically connected knowledge triples, to identify and integrate supporting evidence from the retrieved documents for answering questions. Specifically, TRACE employs a KG Generator to create a knowledge graph (KG) from the retrieved documents, and then uses a novel Autoregressive Reasoning Chain Constructor to build reasoning chains. Experimental results on three multi-hop QA datasets show that TRACE achieves an average performance improvement of up to 14.03% compared to using all the retrieved documents. Moreover, the results indicate that using reasoning chains as context, rather than the entire documents, is often sufficient to correctly answer questions.

TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation

Despite the outstanding performance, Neural Architecture Search (NAS) is criticized for massive computation. Recently, Zero-shot NAS has emerged as a promising approach by exploiting Zero-cost (ZC) proxies, which markedly reduce computational demands. Despite this, existing ZC proxies heavily rely on expert knowledge and incur significant trial-and-error costs. Particularly in NLP tasks, most existing ZC proxies fail to surpass the performance of the naive baseline. To address these challenges, we introduce a novel framework, LPZero, which is the first to automatically design zero-cost (ZC) proxies for various tasks, achieving higher ranking consistency than human-designed proxies. Specifically, we model the ZC proxy as a symbolic equation and incorporate a unified proxy search space that encompasses existing ZC proxies, which are composed of a predefined set of mathematical symbols. To heuristically search for the best ZC proxy, LPZero incorporates genetic programming to find the optimal symbolic composition. We propose a Predictive-Pruning Strategy (PPS), which preemptively eliminates unpromising proxies, thereby mitigating the risk of proxy degradation. Extensive experiments on FlexiBERT, GPT-2, and LLaMA-7B demonstrate LPZero's superior ranking ability and performance on downstream tasks compared to current approaches.

LPZero: Language Model Zero-cost Proxy Search from Zero

While current Automated Essay Scoring (AES) methods demonstrate high scoring agreement with human raters, their decision-making mechanisms are not fully understood. Our proposed method, using counterfactual intervention assisted by Large Language Models (LLMs), reveals that BERT-like models primarily focus on sentence-level features, whereas LLMs such as GPT-3.5, GPT-4 and Llama-3 are sensitive to conventions & accuracy, language complexity, and organization, indicating a more comprehensive rationale alignment with scoring rubrics. Moreover, LLMs can discern counterfactual interventions when giving feedback on essays. Our approach improves understanding of neural AES methods and can also apply to other domains seeking transparency in model-driven decisions.

Beyond Agreement: Diagnosing the Rationale Alignment of Automated Essay Scoring Methods based on Linguistically-informed Counterfactuals

Text simplification is crucial for making texts more accessible, yet current research primarily focuses on sentence-level simplification, neglecting document-level simplification and the different reading levels of target audiences. To bridge these gaps, we introduce ExpertEase, a multi-agent framework for grade-specific document simplification using Large Language Models (LLMs). ExpertEase simulates real-world text simplification by introducing expert, teacher, and student agents that cooperate on the task and rely on external tools for calibration. Experiments demonstrate that this multi-agent approach significantly enhances LLMs' ability to simplify reading materials for diverse audiences. Furthermore, we evaluate the performance of LLMs varying in size and type, and compare LLM-generated texts with human-authored ones, highlighting their potential in educational resource development and guiding future research.

ExpertEase: A Multi-Agent Framework for Grade-Specific Document Simplification with Large Language Models

Generating plain biomedical summaries with Large Language Models (LLMs) can enhance the accessibility of biomedical knowledge to the public. However, how faithful the generated summaries are remains an open yet critical question. To address this, we propose FaReBio, a benchmark dataset with expert-annotated Faithfulness and Reasoning on plain Biomedical Summaries. This dataset consists of 175 plain summaries ($,445 sentences) generated by seven different LLMs, paired with source articles. Using our dataset, we identify the performance gap of LLMs in generating faithful plain biomedical summaries and observe a negative correlation between abstractiveness and faithfulness. We also show that current faithfulness evaluation metrics do not work well in the biomedical domain and confirm the over-confident tendency of LLMs as faithfulness evaluators. To better understand the faithfulness judgements, we further benchmark LLMs in retrieving supporting evidence and show the gap of LLMs in reasoning faithfulness evaluation at different abstractiveness levels. Going beyond the binary faithfulness labels, coupled with the annotation of supporting sentences, our dataset could further contribute to the understanding of faithfulness evaluation and reasoning.

Understanding Faithfulness and Reasoning of Large Language Models on Plain Biomedical Summaries

This paper introduces a novel model compression approach through dynamic layer-specific pruning in Large Language Models (LLMs), enhancing the traditional methodology established by SliceGPT. By transitioning from constant to dynamic slicing, our method leverages the newly proposed Layer Redundancy (LR) score, which assesses how much change each layer changes its input by measuring the cosine similarity of the input to the output of the layer. We use this score to prune parts of individual layers based on redundancy in such a way that the average pruned percentage for all layers is a fixed value. 
We conducted extensive experiments using models like Llama3-8B and Mistral-7B on multiple datasets, evaluating different slicing bases and percentages to determine optimal configurations that balance efficiency and performance. Our findings show that our dynamic slicing approach not only maintains but, in many cases, enhances model performance compared to the baseline established by constant slicing methods. For instance, in several settings, we see performance improvements of up to 5% over the SliceGPT baseline.
Additionally, a perplexity decrease by as much as 7% was observed across multiple benchmarks, validating the effectiveness of our method. The code, model weights, and datasets are open-sourced at - https://github.com/RazvanDu/DynamicSlicing

Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy

We advocate for a strong integration of Computational Creativity (CC) with research in large language and vision models (LLVMs) to address a key limitation of these models, i.e., creative problem solving. We present preliminary experiments showing how CC principles can be applied to address this limitation. Our goal is to foster discussions on creative problem solving in LLVMs and CC at prestigious ML venues.

Position Paper: Creative Problem Solving in Large Language and Vision Models -- What Would it Take?

Large language model (LLM) leads to a surge of autonomous GUI agents for smartphone, which completes a task triggered by natural language through predicting a sequence of actions of API. Even though the task highly relies on past actions and visual observations, existing studies typically consider little semantic information carried out by intermediate screenshots and screen operations. To address this, this work presents Chain-of-Action-Thought (dubbed CoAT), which takes the description of the previous actions, the current screen, and more importantly the action thinking of what actions should be performed and the outcomes led by the chosen action. We demonstrate that, in a zero-shot setting upon three off-the-shelf LMMs, CoAT significantly improves the action prediction compared to previous proposed context modeling. To further facilitate the research in this line, we construct a dataset Android-In-The-Zoo (AitZ), which contains 18,643 screen-action pairs together with chain-of-action-thought annotations. Experiments show that fine-tuning a 1B model (i.e. AUTO-UI-base) on our AitZ dataset achieves on-par performance with CogAgent-Chat-18B.

Android in the Zoo: Chain-of-Action-Thought for GUI Agents

Multi-attribute controllable text generation (CTG) aims to generate fluent text satisfying multiple attributes, which is an important and challenging task. The majority of previous research on multi-attribute CTG has ignored the interrelations of attributes that affect the performance of text generation. Recently, several work considers the attribute relations by explicitly defining them as $\textit{inhibtory}$. We argue that for multi-attribute CTG, the attribute relations are not fixed, which can be not only $\textit{inhibtory}$ but $\textit{promotive}$ as well. In this paper, we tackle the multi-attribute CTG problem by explicitly identifying the above attribute relations for the first time and propose TARA, which employs token-level attribute relation adaptation and representation to generate text with the balanced multi-attribute control. Experimental results on the benchmark dataset demonstrate the effectiveness of our proposed method.

Downloads

Next from EMNLP 2024

Unsupervised Hierarchical Topic Modeling via Anchor Word Clustering and Path Guidance

Similar lecture

From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment