China

Schema linking is a critical bottleneck in applying existing Text-to-SQL models to realworld, large-scale, multi-database environments. Through error analysis, we identify two major challenges in schema linking: (1)Database Retrieval: accurately selecting the target database from a large schema pool, while effectively filtering out irrelevant ones; and (2) Schema Item Grounding: precisely identifying the relevant tables and columns within complex and often redundant schemas for SQL generation. Based on these, we introduce LinkAlign, a novel framework tailored for large-scale databases with thousands of fields. LinkAlign comprises three key steps: multi-round semantic enhanced retrieval and irrelevant information isolation for Challenge 1, and schema extraction enhancement for Challenge 2. Each stage supports both Agent and Pipeline execution modes, enabling balancing efficiency and performance via modular design. To enable more realistic evaluation, we construct AmbiDB, a synthetic dataset designed toreflect the ambiguity of real-world schema linking. Experiments on widely-used Text-to-SQLbenchmarks demonstrate that LinkAlign consistently outperforms existing baselines on all schema linking metrics. Notably, it improvesthe overall Text-to-SQL pipeline and achieves a new state-of-the-art score of 33.09% on theSpider 2.0-Lite benchmark using only open-source LLMs, ranking first on the leaderboardat the time of submission. The code will be open-sourced after the review period.

EMNLP 2025

LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL

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."<br>

*Message from the General Chair, Dirk Hovy*

[**Link to Conference Handbook**](https://drive.google.com/file/d/1johU5QqVVYO4RfH7QcIORr7qrVBdzdwC/view?usp=sharing)





<br>

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

Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources (e.g., fetching information from public websites), tool responses may contain injected instructions that covertly influence agent behaviors and lead to malicious outcomes, a threat referred to as Indirect\ Prompt\ Injection (IPI). Existing defenses typically rely on advanced prompting strategies or auxiliary detection models. While these methods have demonstrated some effectiveness, they fundamentally rely on assumptions about the model's inherent security, which lacks structural constraints on agent behaviors. As a result, agents still retain unrestricted access to tool invocations, leaving them vulnerable to stronger attack vectors that can bypass the security guardrails of the model. To\ prevent\ malicious\ tool\ invocations\ at\ the\ source, we propose a novel defensive task execution paradigm, called IPIGuard, which models the agents' task execution process as a traversal over a planned Tool\ Dependency\ Graph (TDG). By explicitly decoupling action planning from interaction with external data, IPIGuard significantly reduces unintended tool invocations triggered by injected instructions, thereby enhancing robustness against IPI attacks. Experiments on the AgentDojo benchmark show that IPIGuard achieves a superior balance between effectiveness and robustness, paving the way for the development of safer agentic systems in dynamic environments.

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents

As Model Context Protocol (MCP) introduces an easy-to-use ecosystem for users and developers, it also brings underexplored safety risks. Its decentralized architecture, which separates clients and servers, poses unique challenges for systematic safety analysis. This paper proposes a novel framework to enhance MCP safety. Guided by the MAESTRO framework, we first analyze the missing safety mechanisms in MCP, and based on this analysis, we propose the Model Contextual Integrity Protocol (MCIP), a refined version of MCP that addresses these gaps. Next, we develop a fine-grained taxonomy that captures a diverse range of unsafe behaviors observed in MCP scenarios. Building on this taxonomy, we develop benchmark and training data that support the evaluation and improvement of LLMs’ capabilities in identifying safety risks within MCP interactions. Leveraging the proposed benchmark and training data, we conduct extensive experiments on state-of-the-art LLMs. The results highlight LLMs' vulnerabilities in MCP interactions and demonstrate that our approach substantially improves their safety performance.

MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol

The task of translating natural language questions into query languages has long been a central focus in semantic parsing. Recent advancements in Large Language Models (LLMs) have significantly accelerated progress in this field. However, existing studies typically focus on a single query language, resulting in methods with limited generalizability across different languages. In this paper, we formally define the Text-to-Query task paradigm, unifying semantic parsing tasks across various query languages. We identify query skeletons as a shared optimization target of Text-to-Query tasks, and propose a general dynamic data augmentation framework that explicitly diagnoses model-specific weaknesses in handling these skeletons to synthesize targeted training data. Experiments on three Text-to-Query benchmarks demonstrate that our method achieves state-of-the-art performance using only a small amount of synthesized data, highlighting the efficiency and generality of our approach and laying a solid foundation for unified research on Text-to-Query tasks.

Skeletons Matter: Dynamic Data Augmentation for Text-to-Query

Construction grammar posits that children acquire constructions (form-meaning pairings) from the statistics of their environment. Recent work supports this hypothesis by showing sensitivity to constructions in pretrained language models (PLMs), including one recent study (Rozner et al, 2025) demonstrating that constructions shape the PLM’s output distribution. However, models under study have generally been trained on developmentally implausible amounts of data, casting doubt on their relevance to human language learning. Here we use Rozner et al.'s methods to evaluate constructional learning in models from the 2024 BabyLM challenge. Our results show that even when trained on developmentally plausible quantities of data, models represent diverse constructions, even hard cases that are superficially indistinguishable. We further find correlational evidence that constructional performance may be functionally relevant: models that better represent constructions perform better on the BabyLM benchmarks.

BabyLM’s First Constructions: Causal interventions provide a signal of learning

Generative AI has established the opportunity to readily transform content from one medium to another. This capability is especially powerful for storytelling, where visual illustrations can illuminate a story originally expressed in text. In this paper, we focus on the task of narrative scene illustration, which involves automatically generating an image depicting a scene in a story. Motivated by recent progress on text-to-image models, we consider a pipeline that uses LLMs as an interface for prompting text-to-image models to generate scene illustrations given raw story text. We apply variations of this pipeline to a prominent story corpus in order to synthesize illustrations for scenes in these stories. We conduct a human annotation task to obtain pairwise quality judgments for these illustrations. The outcome of this process is the SceneIllustrations dataset, which we release as a new resource for future work on cross-modal narrative transformation. Through our analysis of this dataset and experiments modeling illustration quality, we demonstrate that LLMs can effectively verbalize scene knowledge implicitly evoked by story text. Moreover, this capability is impactful for generating and evaluating illustrations.

LLMs Behind the Scenes: Enabling Narrative Scene Illustration

Automatic pronunciation assessment is typically performed by acoustic models trained on audio-score pairs. Although effective, these systems provide only numerical scores, without the information needed to help learners understand their errors. Meanwhile, large language models (LLMs) have proven effective in supporting language learning, but their potential for assessing pronunciation remains unexplored. In this work, we introduce TextPA, a zero-shot, Textual description-based Pronunciation Assessment approach. TextPA utilizes human-readable representations of speech signals, which are fed into an LLM to assess pronunciation accuracy and fluency, while also providing reasoning behind the assigned scores. Finally, a phoneme sequence match scoring method is used to refine the accuracy scores. Our work highlights a previously overlooked direction for pronunciation assessment. Instead of relying on supervised training with audio-score examples, we exploit the rich pronunciation knowledge embedded in written text. Experimental results show that our approach is both cost-efficient and competitive in performance. Furthermore, TextPA significantly improves the performance of conventional audio-score-trained models on out-of-domain data by offering a complementary perspective.

Read to Hear: A Zero-Shot Pronunciation Assessment Using Textual Descriptions and LLMs

Text-to-SQL is the task of translating natural language questions into SQL queries based on relational databases. Different databases implement their own SQL dialects, leading to variations in syntax. As a result, SQL queries designed for one database may not execute properly in another, creating a dialect gap. Existing Text-to-SQL research primarily focuses on specific database systems, limiting adaptability to different dialects. This paper proposes a novel adaptive framework called Dialect-SQL, which employs Object Relational Mapping (ORM) code as an intermediate language to bridge this gap. Given a question, we guide Large Language Models (LLMs) to first generate ORM code, which is then parsed into SQL queries targeted for specific databases. However, there is a lack of high-quality Text-to-Code datasets that enable LLMs to effectively generate ORM code. To address this issue, we propose a bootstrapping approach to synthesize ORM code, where verified ORM code is iteratively integrated into a demonstration pool that serves as in-context examples for ORM code generation. Our experiments demonstrate that Dialect-SQL significantly enhances dialect adaptability, outperforming traditional methods that generate SQL queries directly. Our code and data are released at \url{https://anonymous.4open.science/r/text-to-sql-5F65}.

Dialect-SQL: An Adaptive Framework for Bridging the Dialect Gap in Text-to-SQL

Machine-generated text detection is critical for preventing misuse of large language models (LLMs). Although LLMs have recently excelled at mimicking human writing styles, they still suffer from factual hallucinations manifested as entity-relation inconsistencies with real-world knowledge. Current detection methods inadequately address the authenticity of the entity graph, which is a key discriminative feature for identifying machine-generated content. To bridge this gap, we propose a fact-aware model that assesses discrepancies between textual and factual entity graphs through graph comparison. In order to holistically analyze context information, our approach employs hierarchical feature extraction with gating units, enabling the adaptive fusion of multi-grained features from entity, sentence, and document levels. Experimental results on three public datasets demonstrate that our approach outperforms the state-of-the-art methods. Interpretability analysis shows that our model can capture the differences in entity graphs between machine-generated and human-written texts.

Non-Existent Relationship: Fact-Aware Multi-Level Machine-Generated Text Detection

Aligning language models with user intent is becoming increasingly relevant to enhance user experience. This calls for designing methods that can allow users to control the properties of the language that LMs generate. For example, controlling the length of the generation, the complexity of the language that gets chosen, the sentiment, tone, etc. Most existing work attempts to integrate users' control by conditioning LM generations on natural language prompts or discrete control signals, which are often brittle and hard to scale. In this work, we are interested in *continuous* control signals, ones that exist along a spectrum that can't easily be captured in a natural language prompt or via existing techniques in conditional generation. Through a case study in controlling the precise response-length of generations produced by LMs, we demonstrate how after fine-tuning, behaviors of language models can be controlled via continuous signals---as vectors that are interpolated between a "low" and a "high" token embedding. Our method more reliably exerts response-length control than in-context learning methods or fine-tuning methods that represent the control signal as a discrete signal. Our full open-sourced code and datasets are available at https://anonymous.4open.science/r/CIE-E7C1/

CIE: Controlling Language Model Text Generations Using Continuous Signals

Retrieval-Augmented Generation (RAG) has emerged as a key paradigm for enhancing large language models by incorporating external knowledge. However, current RAG methods exhibit limited capabilities in complex RAG scenarios and suffer from limited task diversity. To address these limitations, we propose RAG-Instruct, a general method for synthesizing diverse and high-quality RAG instruction data based on any source corpus. Our approach leverages (1) five RAG paradigms, which encompass diverse query-document relationships, and (2) instruction simulation, which enhances instruction diversity and quality by utilizing the strengths of existing instruction datasets. Using this method, we construct a 40K instruction dataset from Wikipedia, comprehensively covering diverse RAG scenarios and tasks. Experiments demonstrate that RAG-Instruct effectively enhances LLMs' RAG capabilities, achieving strong zero-shot performance and significantly outperforming various RAG baselines across a diverse set of tasks.

Downloads

Next from EMNLP 2025

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES