China

We introduce TurBLiMP, the first Turkish benchmark of linguistic minimal pairs, designed to evaluate the linguistic abilities of monolingual and multilingual language models (LMs). Covering 16 linguistic phenomena with 1000 minimal pairs each, TurBLiMP fills an important gap in linguistic evaluation resources for Turkish. In designing the benchmark, we give extra attention to two properties of Turkish that remain understudied in current syntactic evaluations of LMs, namely word order flexibility and subordination through morphological processes. Our experiments on a wide range of LMs and a newly collected set of human acceptability judgments reveal that even cutting-edge Large LMs still struggle with grammatical phenomena that are not challenging for humans, and may also exhibit different sensitivities to word order and morphological complexity compared to humans.

EMNLP 2025

TurBLiMP: A Turkish Benchmark of Linguistic Minimal Pairs

linguistic theories

language resources

benchmarking

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
 The conference will be held in Toronto, Canada, July 9-14, 2023. 
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience. 
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**

ACL 2023

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

poster

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Aligning large language models (LLMs) with human preferences is a central challenge for building reliable AI systems. Most existing alignment approaches rely on static signals, such as predefined principles or offline human annotations to guide model behavior toward a fixed approximation of human preferences. However, LLMs can exhibit distributional drift during training, and static alignment mechanisms lack the capacity to adaptively correct misaligned behaviors as they emerge. To address this limitation, we develop a two-stage framework that enables dynamic and continuous alignment. In the first stage, a constitution is continually revised based on observed model behaviors, and models are trained to comply with these evolving principles. In the second stage, this learned constitution is used to guide reinforcement learning, encouraging the model to align with the updated normative signals. We refer to this framework as COCOA: Co-evolution of Constitutions and AI Models. We show that COCOA enables a 7B model to greatly improve safety—raising StrongReject score from 0.741 to 0.935 and Safe-RLHF accuracy from 77.76% to 90.64% without human annotations, reaching performance close to much larger state-of-the-art models.

Governance in Motion: Co-evolution of Constitutions and AI models for Scalable Safety

Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs). However, reward modeling based on the Bradley-Terry (BT) model assumes a global reward function, failing to capture the inherently diverse and heterogeneous human preferences. Hence, such oversimplification limits LLMs from supporting personalization and pluralistic alignment. Theoretically, we show that when human preferences follow a mixture distribution of diverse subgroups, a single BT model has an irreducible error. While existing solutions, such as fine-grained annotations via prompting or structured preference elicitation, help address this issue, they are costly and constrained by predefined attributes, failing to fully capture the richness of human values. In this work, we introduce MiCRo, a two-stage framework that enhances personalized preference learning by leveraging large-scale binary preference datasets without requiring explicit fine-grained annotations. In the first stage, MiCRo employs a mixture of preferences to model diverse human preferences, enabling a flexible representation of diverse value systems. In the second stage, MiCRo integrates an online routing strategy that dynamically adapts mixture weights based on specific context to resolve ambiguity, allowing for efficient and scalable preference adaptation with minimal additional supervision. Experiments on multiple preference datasets demonstrate that MiCRo effectively captures diverse human preferences and significantly improves personalized preference learning on downstream tasks.

MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning

Recent advancements in tool learning have enabled large language models (LLMs) to integrate external tools, enhancing their task performance by expanding their knowledge boundaries. However, relying on tools often introduces trade-offs between performance, speed, and cost, with LLMs sometimes exhibiting overreliance and overconfidence in tool usage. This paper addresses the challenge of aligning LLMs with their knowledge boundaries to make more intelligent decisions about tool invocation. We propose a multi-objective alignment framework that combines probabilistic knowledge boundary estimation with dynamic decision-making, allowing LLMs to better assess when to invoke tools based on their confidence. Our framework includes two methods for knowledge boundary estimation—consistency-based and absolute estimation—and two training strategies for integrating these estimates into the model’s decision-making process. Experimental results on various tool invocation scenarios demonstrate the effectiveness of our framework, showing significant improvements in tool efficiency by reducing unnecessary tool usage.

Alignment for Efficient Tool Calling of Large Language Models

Large language models (LLMs) excel at generating long-form responses, but evaluating their factuality remains challenging due to complex inter-sentence dependencies within the generated facts. Prior solutions predominantly follow a decompose-decontextualize-verify pipeline but often fail to capture essential context and miss key relational facts. In this paper, we introduce VeriFact, a factuality evaluation framework designed to enhance fact extraction by identifying and resolving incomplete and missing facts to support more accurate verification results. Moreover, we introduce FactRBench , a benchmark that evaluates both precision and recall in long-form model responses, whereas prior work primarily focuses on precision. FactRBench provides reference fact sets from advanced LLMs and human-written answers, enabling recall assessment. Empirical evaluations show that VeriFact significantly enhances fact completeness and preserves complex facts with critical relational information, resulting in more accurate factuality evaluation. Benchmarking various open- and close-weight LLMs on FactRBench indicate that larger models within same model family improve precision and recall, but high precision does not always correlate with high recall, underscoring the importance of comprehensive factuality assessment.

VeriFact: Enhancing Long-Form Factuality Evaluation with Refined Fact Extraction and Reference Facts

Text-to-Image (T2I) models have made remarkable progress in generating images from text prompts, but their output quality and safety still depend heavily on how prompts are phrased. Existing safety methods typically refine prompts using large language models (LLMs), but they overlook the images produced, which can result in unsafe outputs or unnecessary changes to already safe prompts. To address this, we propose an iterative prompt refinement algorithm that uses Vision Language Models (VLMs) to analyze both the input prompts and the generated images. By leveraging visual feedback, our method refines prompts more effectively, improving safety while maintaining user intent and reliability comparable to existing LLM-based approaches. Additionally, we introduce a new dataset labeled with both textual and visual safety signals using off-the-shelf multi-modal LLM, enabling supervised fine-tuning. Experimental results demonstrate that our approach produces safer outputs without compromising alignment with user intent, offering a practical solution for generating safer T2I content. textbftextcolorredWARNING: This paper contains examples of harmful or inappropriate images generated by models.

Iterative Prompt Refinement for Safer Text-to-Image Generation

Hierarchical text classification aims to classify documents into multiple labels within a hierarchical taxonomy, making it an essential yet challenging task in natural language processing. Recently, using Large Language Models (LLM) to tackle hierarchical text classification in a zero-shot manner has attracted increasing attention due to their cost-efficiency and flexibility. Given the challenges of understanding the hierarchy, various HTC prompting strategies have been explored to elicit the best performance from LLMs. However, our empirical study reveals that LLMs are highly sensitive to these prompting strategies---(i) within a task, different strategies yield substantially different results, and (ii) across various tasks, the relative effectiveness of a given strategy varies significantly. To address this, we propose a novel ensemble method, HiEPS, which integrates the results of diverse prompting strategies to promote LLMs' reliability. We also introduce a path-valid voting mechanism for ensembling, which selects a valid result with the highest path frequency score. Extensive experiments on three benchmark datasets show that HiEPS boosts the performance of single prompting strategies and achieves SOTA results

Ensembling Prompting Strategies for Zero-Shot Hierarchical Text Classification with Large Language Models

Instruction-following made modern large language models (LLMs) helpful assistants. However, the key to taming LLMs on complex instructions remains mysterious, for that there are huge gaps between models trained by open-source community and those trained by leading companies. To bridge the gap, we propose a simple and scalable approach UltraIF for building LLMs that can follow complex instructions with open-source data. UltraIF first decomposes real-world user prompts into simpler queries, constraints, and corresponding evaluation questions for the constraints. Then, we train an UltraComposer to compose constraint-associated prompts with evaluation questions. This prompt composer allows us to synthesize complicated instructions as well as filter responses with evaluation questions. In our experiment, for the first time, we successfully align LLaMA-3.1-8B-Base to catch up with its instruct version on 5 instruction-following benchmarks without any benchmark information, using only 8B model as response generator and evaluator. The aligned model also achieved competitive scores on other benchmarks. Moreover, we also show that UltraIF could further improve LLaMA-3.1-8B-Instruct through self-alignment, motivating broader use cases for the method.

UltraIF: Advancing Instruction Following from the Wild

Large language models (LLMs) have demonstrated significant potential in enhancing dense retrieval through query augmentation. However, most existing methods treat the LLM and the retriever as separate modules, overlooking the alignment between generation and ranking objectives. In this work, we propose ExpandR, a unified LLM-augmented dense retrieval framework that jointly optimizes both the LLM and the retriever. ExpandR employs the LLM to generate semantically rich query expansions, which are leveraged to enhance the retriever's training. Simultaneously, the LLM is trained using Direct Preference Optimization (DPO), guided by a carefully designed reward function that balances retrieval effectiveness and generation consistency. This joint optimization paradigm enables mutual adaptation between the LLM and the retriever, resulting in query expansions that are both informative and well-suited for retrieval. Experimental results on multiple benchmarks show that ExpandR consistently outperforms strong baselines, achieving more than a 5% improvement in retrieval performance. All code will be publicly released on GitHub.

ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance

Large language models (LLMs) often exhibit limited performance on domain-specific tasks due to the natural disproportionate representation of specialized information in their training data and the static nature of these datasets. Knowledge scarcity and temporal lag create knowledge gaps for domain applications. While post-training on domain datasets can embed knowledge into models, existing approaches have some limitations. Continual Pre-Training (CPT) treats all tokens in domain documents with equal importance, failing to prioritize critical knowledge points, while supervised fine-tuning (SFT) with question-answer pairs struggles to develop the coherent knowledge structures necessary for complex reasoning tasks. To address these challenges, we propose Reinforcement Learning from Augmented Generation (RLAG). Our approach iteratively cycles between sampling generations and optimizing the model through calculated rewards, effectively embedding critical and contextually coherent domain knowledge. We select generated outputs with the highest log probabilities as the sampling result, then compute three tailored reward metrics to guide the optimization process. To comprehensively evaluate domain expertise, we assess answer accuracy and the rationality of explanations generated for correctly answered questions. Experimental results across medical, legal, astronomy, and current events datasets demonstrate that our proposed method significantly outperforms baseline approaches. Our code and data will be made publicly available upon publication.

Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation

Seminal work by Huebner et al. (2021) showed that language models (LMs) trained on English Child-Directed Language (CDL) can outperform LMs trained on an equal amount of adult-directed text like Wikipedia. However, it remains unclear whether these results generalize across languages, architectures, and evaluation settings. We test this by comparing models trained on CDL vs. Wikipedia across two LM objectives (masked and causal), three languages (English, French, German), and three syntactic minimal pair benchmarks. Our results on these benchmarks show inconsistent benefits of CDL, which in most cases is outperformed by Wikipedia models. We then identify various shortcomings in these benchmarks, and introduce a novel testing methodology, FIT-CLAMS, which uses a frequency-controlled design to enable balanced comparisons across training corpora. Through minimal pair evaluations and regression analysis we show that training on CDL does not yield stronger generalizations for acquiring syntax and highlight the importance of controlling for frequency effects when evaluating syntactic ability.

Downloads

Next from EMNLP 2025

Governance in Motion: Co-evolution of Constitutions and AI models for Scalable Safety

Similar lecture

A Diverse Set of Freely Available Linguistic Resources for Turkish