China

We present a novel approach to conversational agent evaluation using Persona-driven User Simulations based on Large Language Models (LLMs). Our methodology first uses LLMs to generate diverse customer personas, which are then used to configure a single LLM-based user simulator. This simulator evaluates SalesBot 2.0, a proactive conversational sales agent. We introduce a dataset of these personas, along with corresponding goals and conversation scenarios, enabling comprehensive testing across different customer types with varying assertiveness levels and precision of needs. Our evaluation framework assesses both the simulator&#39;s adherence to persona instructions and the bot&#39;s performance across multiple dimensions, combining human annotation with LLM-as-a-judge assessments using commercial and open-source models. Results demonstrate that our LLM-based simulator effectively emulates nuanced customer roles, and that cross-selling strategies can be implemented with minimal impact on customer satisfaction, varying by customer type.

EMNLP 2025

Evaluating Conversational Agents with Persona-driven User Simulations based on Large Language Models: A Sales Bot Case Study

persona-driven

persona-based

user simulator

dialogue evaluation

persona

### 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)

We present a novel approach to conversational agent evaluation using Persona-driven User Simulations based on Large Language Models (LLMs). Our methodology first uses LLMs to generate diverse customer personas, which are then used to configure a single LLM-based user simulator. This simulator evaluates SalesBot 2.0, a proactive conversational sales agent. We introduce a dataset of these personas, along with corresponding goals and conversation scenarios, enabling comprehensive testing across different customer types with varying assertiveness levels and precision of needs. Our evaluation framework assesses both the simulator's adherence to persona instructions and the bot's performance across multiple dimensions, combining human annotation with LLM-as-a-judge assessments using commercial and open-source models. Results demonstrate that our LLM-based simulator effectively emulates nuanced customer roles, and that cross-selling strategies can be implemented with minimal impact on customer satisfaction, varying by customer type.

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.

Online shoppers often initiate their journey with only a vague idea of what they need, forcing them to iterate over search results until they eventually discover a suitable product. We formulate this scenario as product demand clarification: starting from an ambiguous query, an agent must iteratively ask clarifying questions, progressively refine the user's intent, and retrieve increasingly relevant items. To tackle this challenge, we present **ProductAgent**, a fully autonomous conversational information-seeking agent that couples large language models with a set of domain-specific tools. ProductAgent maintains a structured memory of the dialogue, summarizes candidate products into concise feature statistics, generates strategic clarification questions, and performs retrieval over hybrid (symbolic + dense) indices in a closed decision loop. To measure real–world effectiveness, we further introduce **PROCLARE**, a PROduct CLArifying REtrieval benchmark that pairs ProductAgent with an LLM-driven user simulator, thereby enabling large-scale and reproducible evaluation without human annotation. On 2,000 automatically generated sessions, retrieval metrics improve monotonically with the number of turns, validating that ProductAgent captures and refines user intent through dialogue.

ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questions

Chinese Spelling Correction (CSC) aims to detect and correct spelling errors in given sentences. 
Recently, multi-domain CSC has gradually attracted the attention of researchers because it is more practicable.
In this paper, we focus on the key flaw of the CSC model when adapting to multi-domain scenarios: the tendency to forget previously acquired knowledge upon learning new domain-specific knowledge (i.e., **catastrophic forgetting**).
To address this, we propose a novel model-agnostic **M**ulti-stage **K**nowledge **T**ransfer (**MKT**) framework with an evolving teacher model and dynamic distillation weights for knowledge transfer in each domain, rather than focusing solely on new domain knowledge.
It deserves to be mentioned that we are the first to apply continual learning methods to the multi-domain CSC task. 
Experiments. prove our method's effectiveness over traditional approaches, highlighting the importance of overcoming catastrophic forgetting to enhance model performance.

MKT: A Multi-Stage Knowledge Transfer Framework to Mitigate Catastrophic Forgetting in Multi-Domain Chinese Spelling Correction

This paper presents Ryt AI, an LLM-native agentic framework that powers Ryt Bank to enable customers to execute core financial transactions through natural language conversation. This represents the first global regulator-approved deployment worldwide where conversational AI functions as the primary banking interface, in contrast to prior assistants that have been limited to advisory or support roles. Built entirely in-house, Ryt AI is powered by ILMU, a closed-source LLM developed internally, and replaces rigid multi-screen workflows with a single dialogue orchestrated by four LLM-powered agents (Guardrails, Intent, Payment, and FAQ). Each agent attaches a task-specific LoRA adapter to ILMU, which is hosted within the bank's infrastructure to ensure consistent behavior with minimal overhead. Deterministic guardrails, human-in-the-loop confirmation, and a stateless audit architecture provide defense-in-depth for security and compliance. The result is Banking Done Right: demonstrating that regulator-approved natural-language interfaces can reliably support core financial operations under strict governance.

Banking Done Right: Redefining Retail Banking with Language-Centric AI

Fine-tuning large language models (LLMs) with backpropagation--even for a subset of parameters such as LoRA--can be much more memory-consuming than inference and is often deemed impractical for resource-constrained mobile devices. Alternative methods, such as zeroth-order optimization (ZO), can greatly reduce the memory footprint but come at the cost of significantly slower model convergence (10× to 100× more steps than backpropagation). We propose a memory-efficient implementation of backpropagation (MeBP) on mobile devices that allows flexible trade-offs between memory usage and compute time, while converging faster and achieving better performance than the ZO baseline. We verify the effectiveness of MeBP on an iPhone 15 Pro Max and show that various LLMs, ranging from 0.5B to 4B parameters, can be fine-tuned using less than 1GB of memory.

Memory-Efficient Backpropagation for Fine-Tuning LLMs on Resource-Constrained Mobile Devices

Running Large Language Models (LLMs) on edge devices is constrained by high compute and memory demands—posing a barrier for real-time applications in industries like healthcare, education, and embedded systems. Current solutions such as quantization, pruning, and retrieval-augmented generation (RAG) offer only partial optimizations and often compromise on speed or accuracy.


We introduce HOLA, an end-to-end optimization framework for efficient LLM deployment. Internally, it leverages Hierarchical Speculative Decoding (HSD) for faster inference without quality loss. Externally, AdaComp-RAG adjusts retrieval complexity based on context needs. Together with Lo-Bi, which blends structured pruning (LoRA) and quantization, HOLA delivers significant gains: +17.6% EMA on GSM8K, +10.5% MCA on ARC, and reduced latency and memory on edge devices like Jetson Nano—proving both scalable and production-ready. Our code is available at: \url{https://anonymous.4open.science/r/HOLA_Codebase-FB1E/README.md}

LLMs on a Budget? Say HOLA

E-commerce ad platforms enforce content policies and review created ads before publication, with casing requirements playing a critical role in maintaining readability and brand consistency. Existing NER-based transformer models have been widely used for casing correction, but they process characters independently in a classification-based manner, failing to capture sentence level contextual dependencies, making them less reliable when handling unseen or ad-specific terms, e.g., brand names. LLMs like ChatGPT offer better generalization to proper nouns, but they are expensive and have high latency. Besides, generative model can suffer from hallucination. To address these challenges, we propose a two-stage approach: (1) an LLM-based Agent leveraging Chain-of-Actions (CoA) to enforce casing policies while accurately handling ads-specific terms, such as brand names, and (2) a lightweight generative model that preserves the LLM Agent's knowledge while significantly reducing latency and costs. We design a novel in-context decoding strategy, which avoids hallucinations. Our approach outperforms NER-based methods and achieves near-LLM Agent performance, making it a scalable and efficient solution for real-world ad compliance automation.

Learning from LLM Agents: In-Context Generative Models for Text Casing in E-Commerce Ads

We report on experiments on information extraction (IE) from EU Acquis, the European Union law. We introduce a new IE task of Information Provision Activity Requirement Extraction, which focuses on the identification of text fragments which introduce an obligation to provide information and extraction of structured information therefrom on the key entities involved and temporal modalities. We compare various technologies for this task, including, knowledge-, classical ML-, transformer-, and generative AI-based approaches on a benchmark corpus specifically created for this study.

Extraction of Information Provision Activity Requirements from EU-Acquis

Knowledge graphs (KGs) enhance pretrained language models by incorporating additional knowledge, improving their performance in specialized fields, for example, helping models learn domain-specific relationships between documents that might otherwise be missed. In the process industry, text logs contain crucial information about daily operations, such as events, instructions, and incident reports, and are often structured as sparse KGs. This paper explores how SciNCL, a graph-aware neighborhood contrastive learning methodology originally designed for scientific publications, can be adapted to the process industry domain. We use several KGs to train graph embedding (GE) models, which we then use to generate synthetic training datasets for a domain-specific text encoder. Our experiments demonstrate that language models fine-tuned with triplets derived from GE outperform a state-of-the-art mE5-large text encoder by 12-13.5% (6.68-7.54p) on the proprietary process industry text embedding benchmark (PITEB) while being 3-5 times smaller in size.

Contrastive Learning Using Graph Embeddings for Domain Adaptation of Language Models in the Process Industry

Large language models usually suffer from multiple-file coding scenarios where strong inter-file dependencies manifest, typically demonstrated in SWE-bench. To mitigate this issue, we propose Think-Search-Patch (TSP), a retrieval-augmented reasoning framework for repository-level code repair. In the Think stage, our system breaks down a coding task and creates clear search query. Next, in the Search stage, it retrieves relevant code snippets using models like E5. In the final Patch stage, it generates standardized patches based on the key snippets. In addition the proposed framework, we enhance system reliability through a two-stage training process. In the first stage, the system undergoes supervised fine-tuning (SFT) on our TSP dataset. In the subsequent stage, we employ rejection sampling with correction to generate preference pairs for Direct Preference Optimization (DPO) training, thereby reducing errors in the intermediate phases. Experimental results demonstrate that TSP framework enhances retrieval accuracy and repair success on SWE-bench Lite, even surpassing models with a larger size in managing extensive code contexts and successfully addressing bugs spanning across multiple files. All data and code will be available soon at GitHub.

Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair

LLM agents show promise for vulnerability testing. We however lack benchmarks to evaluate and compare solutions. AutoPenBench covers this need offering an open benchmark for the evaluation of vulnerability testing agents. It includes 33 tasks, ranging from introductory exercises to actual vulnerable systems. It supports MCP, enabling the comparison of agent capabilities. We introduce milestones per task, allowing the comparison of intermediate steps where agents struggle. To illustrate the use of AutoPenBench we evaluate autonomous and human-assisted agent architectures. The former achieves 21\% success rates, insufficient for production, while human-assisted agents reach 64\% success, indicating a viable industrial path. AutoPenBench is offered as open source and enables fair comparison of agents.

Downloads

Next from EMNLP 2025

ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questions

Similar lecture

DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona Modeling

.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

ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questions

Similar lecture

DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona Modeling

Downloads