China

We present a novel neurosymbolic framework for RDF-to-text generation, in which the model is “trained” through collaborative interactions among multiple LLM agents rather than traditional backpropagation. The LLM agents produce rule-based Python code for a generator for the given domain, based on RDF triples only, with no in-domain human reference texts. The resulting system is fully interpretable, requires no supervised training data, and generates text nearly instantaneously using only a single CPU. 
Our experiments on the WebNLG and OpenDialKG data show that outputs produced by our approach reduce hallucination, with only slight fluency penalties compared to finetuned or prompted language models.

EMNLP 2025

LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators

rdf-to-text

neurosymbolic

interpretability

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.

Alignment is no longer a luxury; it is a necessity. As large language models (LLMs) enter high-stakes domains like education, healthcare, governance, and law, their behavior must reliably reflect human-aligned values and safety constraints. Yet current evaluations rely heavily on behavioral proxies such as refusal rates, G-Eval scores, and toxicity classifiers, all of which have critical blind spots. Aligned models are often vulnerable to jailbreaking, stochasticity of generation, and alignment faking. To address this issue, we introduce the **Alignment Quality Index (AQI)**. This novel geometric and prompt-invariant metric empirically assesses LLM alignment by analyzing the separation of safe and unsafe activations in latent space. By combining measures such as the *Davies-Bouldin score (DBS)*, *Dunn index (DI)*, *Xie-Beni index (XBI)*, and *Calinski-Harabasz index (CHI)* across various formulations, AQI captures clustering quality to detect hidden misalignments and jailbreak risks, even when outputs appear compliant. AQI also serves as an early warning signal for alignment faking, offering a robust, decoding-invariant tool for behavior-agnostic safety auditing. Additionally, we propose the **LITMUS** dataset to facilitate robust evaluation under these challenging conditions. Empirical tests on LITMUS across different models trained under DPO, GRPO, and RLHF conditions demonstrate AQI's correlation with external judges and ability to reveal vulnerabilities missed by refusal metrics. We make our implementation publicly available to foster future research in this area.

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations

Every year, the European Union and its member states allocate millions of euros to fund various development initiatives. However, the increasing number of applications received for these programs often creates significant bottlenecks in evaluation processes, due to limited human capacity. In this work, we detail the real-world deployment of AI-assisted evaluation within the pipeline of two government initiatives: (i) corporate applications aimed at international business expansion, and (ii) citizen reimbursement claims for investments in energy-efficient home improvements. While these two cases involve distinct evaluation procedures, our findings confirm that AI effectively enhanced processing efficiency and reduced workload across both types of applications. Specifically, in the citizen reimbursement claims initiative, our solution increased reviewer productivity by 20.1%, while keeping a negligible false-positive rate based on our test set observations. These improvements resulted in an overall reduction of more than 2 months in the total evaluation time, illustrating the impact of AI-driven automation in large-scale evaluation workflows.

Leveraging LLMs to Streamline the Review of Public Funding Applications

Answering "Where is the X button?" with "It's next to the Y button" is unhelpful if the user knows neither location. Useful answers require obvious landmarks as a reference point. We address this by generating from a vehicle dashboard diagram a spatial knowledge graph (SKG) that shows the spatial relationship between a dashboard component and its nearby landmarks and using the SKG to help answer questions. We evaluate three distinct generation pipelines (Per-Attribute, Per-Component, and a Single-Shot baseline) to create the SKG using Large Vision-Language Models (LVLMs). On a new 65-vehicle dataset, we demonstrate that a decomposed Per-Component pipeline is the most effective strategy for generating a high-quality SKG; the graph produced by this method, when evaluated with a novel Significance score, identifies landmarks achieving 71.3% agreement with human annotators. This work enables downstream QA systems to provide more intuitive, landmark-based answers.

Generating Spatial Knowledge Graphs from Automotive Diagrams for Question Answering

In the field of urban planning, existing Vision-Language Models (VLMs) frequently fail to effectively analyze planning maps, which are critical for urban planners and educational contexts. Planning maps require specialized understanding of spatial configurations, regulatory requirements, and multi-scale analysis.


To address this challenge, we introduce PlanGPT-VL, the first domain-specific VLM tailored for urban planning maps. PlanGPT-VL employs three innovations:
(1) PlanAnno-V framework for high-quality VQA data synthesis,
(2) Critical Point Thinking (CPT) to reduce hallucinations through structured verification, and
(3) PlanBench-V benchmark for systematic evaluation.


Evaluation on PlanBench-V shows that PlanGPT-VL outperforms general-purpose VLMs on planning map interpretation tasks, with our 7B model achieving performance comparable to larger 72B models.

PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models

Retrieval-Augmented Generation (RAG) has shown strong performance in open-domain tasks, but its effectiveness in industrial domains is limited by a lack of domain understanding and document structural elements (DSE) such as tables, figures, charts, and formula.
To address this challenge, we propose an efficient knowledge distillation framework that transfers complementary knowledge from both Large Language Models (LLMs) and Vision-Language Models (VLMs) into a compact domain-specific retriever.
Extensive experiments and analysis on real-world industrial datasets from shipbuilding and electrical equipment domains demonstrate that the proposed framework improves both domain understanding and visual-structural retrieval, outperforming larger baselines while requiring significantly less computational complexity.

Distilling Cross-Modal Knowledge into Domain-Specific Retrievers for Enhanced Industrial Document Understanding

Generating effective query suggestions in conversational search requires aligning model outputs with user preferences, which is challenging due to sparse and noisy click signals. We propose \textbf{GQS}, a generative framework that integrates click modeling and preference optimization to enhance real-world user engagement.
GQS consists of three key components: (1) a \textit{Multi-Source CTR Modeling} module that captures diverse contextual signals to estimate fine-grained click-through rates; (2) a \textit{Diversity-Aware Preference Alignment} strategy using CTR-weighted Direct Preference Optimization (DPO), which balances relevance and semantic diversity; and (3) a \textit{CTR-Calibrated Iterative Optimization} process that jointly refines the CTR and generation models across training rounds.
Experiments on two real-world tasks demonstrate that GQS outperforms strong baselines in CTR, relevance, and diversity.

CTR-Guided Generative Query Suggestion in Conversational Search

Learning clients embeddings from sequences of their historic communications is central to financial applications. While large language models (LLMs) offer general world knowledge, their direct use on long event sequences is computationally expensive and impractical in real-world pipelines. In this paper, we propose LATTE a contrastive learning framework that aligns raw event embeddings with semantic embeddings from frozen LLMs. Behavioral features are summarized into short prompts, embedded by the LLM, and used as supervision via contrastive loss. The proposed approach significantly reduces inference cost and input size compared to conventional processing of complete sequence by LLM. We experimentally show that our method outperforms state-of-the-art techniques for learning event sequence representations on real-world financial datasets while remaining deployable in latency-sensitive environments.

LATTE: Learning Aligned Transactions and Textual Embeddings for Bank Clients

Reliable data quality is crucial for downstream analysis of tabular datasets, yet rule-based validation often struggles with inefficiency, human intervention, and high computational costs. We present a three-stage framework that combines statistical inliner detection with LLM-driven rule and code generation. After filtering data samples through traditional clustering, we iteratively prompt LLMs to produce semantically valid quality rules and synthesize their executable validators through code-generating LLMs. To generate reliable quality rules, we aid LLMs with retrieval-augmented generation (RAG) by leveraging external knowledge sources and domain-specific few-shot examples. Robust guardrails ensure the accuracy and consistency of both rules and code snippets. Extensive evaluations on benchmark datasets confirm the effectiveness of our approach.

Quality Assessment of Tabular Data using Large Language Models and Code Generation

Structured information extraction from unstructured text is widely used in LLM-based applications and has critical importance in emerging Software 3.0 systems where LLM agents autonomously interact with APIs and tools. Recent work has addressed this problem by applying large language models directly to extraction tasks using existing JSON schemas, often with constraint decoding or reinforcement learning approaches to ensure syntactic validity. Unfortunately, all of these approaches treat JSON schemas as static contracts designed for human developers and traditional systems, leading to suboptimal extraction performance, frequent hallucinations, and unreliable agent behavior when schemas contain ambiguous or incomplete specifications. In contrast, we recognize that JSON schemas themselves are a form of natural language understanding contract that encodes rules, relationships, and expectations about data structure contracts that LLMs should be able to both interpret and systematically improve. Consequently, we develop PARSE (Parameter Automated Refinement and Schema Extraction), a novel system with two synergistic components: ARCHITECT, which autonomously optimizes JSON schemas for LLM consumption while maintaining backward compatibility through integrated reverse engineering, and SCOPE, which implements reflection-based extraction with combined static and LLM-based guardrails. We evaluate PARSE qualitatively and quantitatively on three datasets including Schema-Guided Dialogue (SGD), Structured Web Data Extraction (SWDE), and internal retail conversation data, and find that it achieves up to 64.7\% improvement in extraction accuracy on SWDE with combined framework improvements reaching 10\% across models, while reducing extraction errors by 92\% within the first retry and maintaining practical latency through optimized schema refinement that reduces reflection overhead by an average of 4.05 seconds.

PARSE: Parameter Automated Refinement and Schema Extraction

The rapid growth of online video content, especially on short video platforms, has created a growing demand for efficient video editing techniques that can condense long-form videos into concise and engaging clips. 
Existing automatic editing methods predominantly rely on textual cues from ASR transcripts and end-to-end segment selection, often neglecting the rich visual context and leading to incoherent outputs. 
In this paper, we propose a Human-Inspired automatic video editing framework (HIVE) that leverages multimodal narrative understanding to address these limitations. 
Our approach incorporates character extraction, dialogue analysis, and narrative summarization through multimodal large language models, enabling a holistic understanding of the video content. 
To further enhance coherence, we apply scene-level segmentation and decompose the editing process into three subtasks: highlight detection, opening/ending selection, and pruning of irrelevant content. 
To facilitate research in this area, we introduce DramaAD, a novel benchmark dataset comprising over 2500 short drama episodes and 500 professionally edited advertisement clips. 
Experimental results demonstrate that our framework consistently outperforms existing baselines across both general and advertisement-oriented editing tasks, significantly narrowing the quality gap between automatic and human-edited videos.

Downloads

Next from EMNLP 2025

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EMNLP 2025

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads