China

Large language models (LLMs) have demonstrated exceptional capabilities in natural language processing tasks but often fall short in maintaining factual accuracy, particularly in knowledge-intensive domains like healthcare. This study introduces LEAF: Learning and Evaluation Augmented by Fact-Checking, a novel framework aimed at improving the factual reliability of LLMs in medical question answering (QA). LEAF comprises three key contributions: (1) the \textbf{Retrieval-Augmented Factuality Evaluator (RAFE)}, a robust fact-checking system using open-source LLMs and domain-specific retrieval corpora to evaluate response accuracy; (2) \textbf{Fact-Check-then-RAG}, an enhanced Retrieval-Augmented Generation method that incorporates fact-checking to guide retrieval without requiring parameter updates; and (3) \textbf{Learning from Fact Check via Self-Training}, a strategy to improve LLM performance through supervised fine-tuning or preference-based learning, using fact-checking results as pseudo-labels. Experimental results show that RAFE outperforms Factcheck-GPT in detecting inaccuracies, Fact-Check-then-RAG effectively corrects errors, and Learning from Fact Check improves performance without labeled data. These findings suggest LEAF as a scalable and robust solution for low-resource settings.

EMNLP 2025

LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models

fact-check

### 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)

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.

Recent advances in large language models (LLMs) have boosted performance across a broad spectrum of natural‑language tasks, yet no single model excels uniformly across domains. Sending each query to the most suitable model mitigates this limitation, but deciding among *all* available LLMs for each query is prohibitively expensive. Both the accuracy and the latency can improve if the decision space for the model choice is first narrowed, followed by selecting the suitable model for the given query.
We introduce Select-then-Route (StR), a two‑stage framework that first *selects* a small, task‑appropriate pool of LLMs and then *routes* each query within that pool through an adaptive cascade. StR first employs a lightweight, *taxonomy‑guided selector* that maps each query to models proven proficient for its semantic class (e.g., reasoning, code, summarisation). Within the selected pool, a *confidence‑based cascade* begins with the cheapest model and escalates only when a multi‑judge agreement test signals low reliability.
Across six public benchmarks of various domains, StR improves the end‑to‑end accuracy from 91.7% (best single model) to 94.3% while reducing inference cost by 4X. Because both the taxonomy and multi-judge evaluation thresholds are tunable, StR exposes a smooth cost–accuracy frontier, enabling users to dial in the trade‑off that best fits their latency and budget constraints.

Select-then-Route : Taxonomy guided Routing for LLMs

Enterprises today are increasingly encouraged to adopt dedicated vector databases for retrieval augmented generation (RAG) in large language model applications.
We propose that, instead, organizations should leverage existing relational databases for retrieval, which many have already deployed, minimizing additional complexity in their software stacks.
To demonstrate the feasibility of this approach, we present QuackIR, an information retrieval (IR) toolkit built on relational database management systems (RDBMSs), with integrations in DuckDB, SQLite, and PostgreSQL. 
Using QuackIR, we benchmark the sparse and dense retrieval capabilities of these popular RDBMSs and demonstrate that their effectiveness is comparable to baselines from established IR toolkits. 
Our results highlight the potential of relational databases as a simpler alternative compared to vector stores for RAG scenarios due to their established widespread usage.

QuackIR: Retrieval in DuckDB and Other Relational Database Management Systems

Recent text-to-image models excel at generating high-quality object-centric images from instructions. However, images should also encapsulate rich interactions between objects, where existing models often fall short, likely due to limited training data and benchmarks for rare interactions. This paper explores a novel application of Multimodal Large Language Models (MLLMs) to benchmark and enhance the generation of interaction-rich images.
We introduce InterActing-1000, an interaction-focused dataset with 1000 LLM-generated fine-grained prompts for image generation covering (1) functional and action-based interactions, (2) multi-subject interactions, and (3) compositional spatial relationships.
To address interaction-rich generation challenges, we propose a decomposition-augmented refinement procedure. Our approach, DetailScribe, leverages LLMs to decompose interactions into finer-grained concepts, uses an MLLM to critique generated images, and applies targeted refinements with a partial diffusion denoising process. Automatic and human evaluations show significantly improved image quality, demonstrating the potential of enhanced inference strategies. Our dataset and code are available at https://detailscribe.github.io/.

Generating Fine Details of Entity Interactions

Interpreting the internal representations of large language models (LLMs) is crucial for their deployment in real-world applications, impacting areas such as AI safety, debugging, and compliance. Sparse Autoencoders facilitate interpretability by decomposing polysemantic activation into a latent space of monosemantic features. However, evaluating the auto-interpretability of these features is difficult and computationally expensive, which limits scalability in practical settings. In this work, we propose SFAL, an alternative evaluation strategy that reduces reliance on LLM-based scoring by assessing the alignment between the semantic neighbourhoods of features (derived from auto-interpretation embeddings) and their functional neighbourhoods (derived from co-occurrence statistics).
Our method enhances efficiency, enabling fast and cost-effective assessments. We validate our approach on large-scale models, demonstrating its potential to provide interpretability while reducing computational overhead, making it suitable for real-world deployment.

SFAL: Semantic-Functional Alignment Scores for Distributional Evaluation of Auto-Interpretability in Sparse Autoencoders

Reward Models (RMs) are key components for evaluating and guiding language model outputs. However, traditional scalar RMs often struggle with incorporating contextual and background information during inference, leading to incomplete evaluations. Generative RMs (GRMs) attempt to address these limitations by generating intermediate reasoning steps. Yet, their uncontrolled black-box nature and inefficiency due to sequential decoding hinder their industrial deployment. Industrial scenarios, such as search and recommendation systems, often involve single-domain tasks requiring evaluation along specific dimensions. In such contexts, diagnosing “bad cases” necessitates structured feedback to identify and optimize dimension-specific issues.
In this paper, we propose the textbfStructural Reward Model (SRM), a modular and interpretable framework integrating side-branch models as auxiliary feature generators. By introducing fine-grained dimensions, SRMs enable interpretable and efficient evaluation, facilitating targeted diagnostics and optimization. This structured approach ensures adaptability and scalability for industrial applications.
Through comprehensive experiments, we demonstrate that SRMs outperform scalar RMs and GRMs in robustness and alignment with human preferences. The modular design further supports efficient optimization for practical scenarios, allowing SRM to provide a practical reward modeling solution for industry.

Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling

We introduce a novel, training free cascade for auto-prompting Large Language Models (LLMs) to assess product quality in e-commerce. Our system requires no training labels or model fine-tuning, instead automatically generating and refining prompts for evaluating attribute quality across tens of thousands of product category–attribute pairs. Starting from a seed of human-crafted prompts, the cascade progressively optimizes instructions to meet catalog-specific requirements. This approach bridges the gap between general language understanding and domain-specific knowledge at scale in complex industrial catalogs. Our extensive empirical evaluations shows the auto-prompt cascade improves precision and recall by 8–10% over traditional chain-of-thought prompting. Notably, it achieves these gains while reducing domain expert effort from 5.1 hours to 3 minutes per attribute - a 99% reduction. Additionally, the cascade generalizes effectively across five languages and multiple quality assessment tasks, consistently maintaining performance gains.

Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogs

Customer service often relies on human agents, which, while effective, can be costly and slower to scale. 
Recent advancements in intelligent chatbots, particularly Retrieval-Augmented Generation (RAG) models, have significantly enhanced efficiency by integrating large language models with external knowledge retrieval. However, developing a multi-turn RAG-based chatbot for real-world customer service presents additional complexities, requiring components like adaptive retrieval and query reformulation. These components typically require substantial annotated data, which is often scarce. To overcome this limitation, we propose methods to automatically generate labels for these components using real customer-agent dialogue data. Specifically, we introduce two labeling strategies for adaptive retrieval: an intent-guided strategy and an explanation-based strategy, along with two query reformulation strategies: natural language query reformulation and keyword-based reformulation. Our experiments reveal that the explanation-based strategy yields the best results for adaptive retrieval, while the keyword-based reformulation improves document retrieval quality.
Our findings offer valuable insights for practitioners working on multi-turn RAG systems.

LLM-Based Dialogue Labeling for Multiturn Adaptive RAG

Financial dialogue transcripts pose a unique challenge for sentence-level information extraction due to their informal structure, domain-specific vocabulary, and variable intent density. We introduce Fin-ExBERT, a lightweight and modular framework for extracting user intent–relevant sentences from annotated financial service calls. Our approach builds on a domain-adapted BERT (Bidirectional Encoder Representations from Transformers) backbone enhanced with LoRA (Low-Rank Adaptation) adapters, enabling efficient fine-tuning using limited labeled data. We propose a two-stage training strategy with progressive unfreezing: initially training a classifier head while freezing the backbone, followed by gradual fine-tuning of the entire model with differential learning rates. To ensure robust extraction under uncertainty, we adopt a dynamic thresholding strategy based on probability curvature (elbow detection), avoiding fixed cutoff heuristics. Empirical results show strong precision and F1 performance on real-world transcripts, with interpretable output suitable for downstream auditing and question-answering workflows. The full framework supports batched evaluation, visualization, and calibrated export, offering a deployable solution for financial dialogue mining.

Fin-ExBERT: User Intent based Text Extraction in Financial Context using Graph-Augmented BERT and trainable Plugin

Large Language Models (LLMs) can be used to convert natural language (NL) instructions into structured business process automation (BPA) process artifacts.
This paper contributes (i) FLOW-BENCH, a high quality dataset of paired NL instructions and business process definitions to
evaluate NL-based BPA tools, and support research in this area, and (ii) FLOW-GEN,
our approach to utilize LLMs to translate NL into an intermediate Python representation that facilitates final conversion into widely adopted business process definition languages, such as BPMN and DMN. We bootstrap FLOW-BENCH by demonstrating how it can be used to evaluate the components of FLOW-GEN across eight LLMs. We hope that FLOW-GEN and FLOW-BENCH
catalyze further research in BPA.

FLOW-BENCH: Towards Conversational Generation of Enterprise Workflows

Automatic Speech Recognition (ASR) is a fundamental and important task in the field of speech and natural language processing. It is an inherent building block in many applications such as voice assistant, speech translation, etc. Despite the advancement of ASR technologies in recent years, it is still inevitable for modern ASR systems to have a substantial number of erroneous recognition due to environmental noise, ambiguity, etc. Therefore, the error correction in ASR is crucial. 


Motivated by this, this paper studies ASR error correction in the Chinese language, which is one of the most popular languages and enjoys a large number of users in the world. We first create a benchmark dataset named \emph{ASR-EC} that contains a wide spectrum of ASR errors generated by industry-grade ASR systems. To the best of our knowledge, it is the first Chinese ASR error correction benchmark. Then, inspired by the recent advances in \emph{large language models (LLMs)}, we investigate how to harness the power of LLMs to correct ASR errors. We apply LLMs to ASR error correction in three paradigms. The first paradigm is prompting, which is further categorized as zero-shot, few-shot, and multi-step. The second paradigm is finetuning, which finetunes LLMs with ASR error correction data. The third paradigm is multi-modal augmentation, which collectively utilizes the audio and ASR transcripts for error correction. Extensive experiments reveal that prompting is not effective for ASR error correction. Finetuning is effective only for a portion of LLMs. Multi-modal augmentation is the most effective method for error correction and achieves state-of-the-art performance.

Downloads

Next from EMNLP 2025

Select-then-Route : Taxonomy guided Routing for LLMs

Similar lecture

FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models

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

Select-then-Route : Taxonomy guided Routing for LLMs

Similar lecture

FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads