China

A broad range of NLP tasks involve selecting relevant text spans from given source texts. Despite this shared objective, such content selection tasks have traditionally been studied in isolation, each with its own modeling approaches, datasets, and evaluation metrics. In this work, we propose instruction-guided content selection (IGCS) as a beneficial unified framework for such settings, where the task definition and any instance-specific request are encapsulated as instructions to a language model. To promote this framework, we introduce IGCSBench, the first unified benchmark covering diverse content selection tasks. Further, we create a large generic synthetic dataset that can be leveraged for diverse content selection tasks, and show that transfer learning with these datasets often boosts performance, whether dedicated training for the targeted task is available or not. Finally, we address generic inference time issues that arise in LLM-based modeling of content selection, assess a generic evaluation metric, and overall propose the utility of our resources and methods for future content selection models.

EMNLP 2025

A Unifying Scheme for Extractive Content Selection Tasks

synthetic-data generation

instruction modeling

small language models

content selection

extractive

summarization

benchmark

transfer learning

2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics.

**Whova App** 
Stay in touch with your fellow conference attendees via the [Whova App](https://whova.com/portal/webapp/nacon_202106/)

**Conference Structure**
https://2021.naacl.org/blog/conference-structure/

**Walkthrough video of how to NAACL 2021** 

Please take a moment to view this video explaining how to navigate the platform, attend sessions network with other attendees. 


<figure class="video_container">
  <iframe src="https://screencast-o-matic.com/watch/crhwbGVh3vx?v=6&ff=1&title=0&controls=1" width=640  height=350  frameborder="0" allowfullscreen="true"> </iframe>
</figure>

<br>
<br>

NAACL 2021

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*





<br>

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

Modern LLMs struggle with efficient updates, as each new pretrained model version requires repeating expensive alignment processes. This challenge also applies to domain- or language-specific models, where fine-tuning on specialized data must be redone for every new base model release. In this paper, we explore the transfer of fine-tuning updates between model versions. Specifically, we derive the *diff vector* (representing the weight changes from fine-tuning) from one *source* model version and apply it to the base model of a different *target* version. Through empirical evaluations on various open-weight model versions, we show that transferring diff vectors can significantly improve the performance of the target base model. For example, transferring the fine-tuning updates from Llama 3.0 8B improves Llama 3.1 8B by 46.9% on IFEval and 15.7% on LiveCodeBench without additional training, even surpassing Llama 3.1 8B Instruct. Furthermore, we demonstrate performance gains on multilingual tasks, with 4.7% and 15.5% improvements on Global MMLU for Malagasy and Turkish, respectively. We observe that these merged models provide stronger initializations for further fine-tuning. Lastly, our controlled experiments suggest that fine-tuning transfer is most effective when source and target models lie in a linearly connected region of parameter space, and we provide a theoretical analysis of our method. Taken together, fine-tuning transfer offers a cost-efficient and practical strategy for continuous LLM development. Our code will be available at https://anonymous.4open.science/r/finetuning-transfer.

Efficient Model Development through Fine-tuning Transfer

Religion and spirituality (R/S) are complex and highly domain-dependent concepts which have long confounded researchers and policymakers. Due to their context-specificity, R/S are difficult to operationalize in conventional archival search strategies, particularly when datasets are very large, poorly accessible, and marked by information noise. As a result, considerable time investments and specialist knowledge is often needed to extract actionable insights related to R/S from general archival sources, increasing reliance on published literature and manual desk reviews. To address this challenge, we present SpiritRAG, an interactive Question Answering (Q\&A) system based on Retrieval-Augmented Generation (RAG). Built using 7,500 United Nations (UN) resolution documents related to R/S in the domains of health and education, SpiritRAG allows researchers and policymakers to conduct complex, context-sensitive database searches of very large datasets using an easily accessible, chat-based web interface. SpiritRAG is lightweight to deploy and leverages both UN documents and user provided documents as source material. A pilot test and evaluation with domain experts on 100 manually composed questions demonstrates the practical value and usefulness of SpiritRAG.

SpiritRAG: A Q&A System for Religion and Spirituality in the United Nations Archive

High-quality annotated data is a cornerstone of modern Natural Language Processing (NLP). While recent methods begin to leverage diverse annotation sources—including Large Language Models (LLMs), Small Language Models (SLMs), and human experts—they often focus narrowly on the labeling step itself. A critical gap remains in the holistic process control required to manage these sources dynamically, addressing complex scheduling and quality-cost trade-offs in a unified manner. Inspired by real-world crowdsourcing companies, we introduce CrowdAgent, a multi-agent system that provides end-to-end process control by integrating task assignment, data annotation, and quality/cost management. It implements a novel methodology that rationally assigns tasks, enabling LLMs, SLMs, and human experts to advance synergistically in a collaborative annotation workflow. We demonstrate the effectiveness of CrowdAgent through extensive experiments on six diverse multimodal classification tasks. The source code is available at https://github.com/QMMMS/CrowdAgent.

CrowdAgent: Multi-Agent Managed Multi-Source Annotation System

Automatic dubbing (AD) aims to replace the original speech in a video with translated speech that maintains precise temporal alignment (isochrony). Achieving natural synchronization between dubbed speech and visual content remains challenging due to variations in speech durations across languages. To address this, we propose an end-to-end AD framework that leverages large language models (LLMs) to integrate translation and timing control seamlessly. At the core of our framework lies Duration-based Translation (DT), a method that dynamically predicts the optimal phoneme count based on source speech duration and iteratively adjusts the translation length accordingly. Our experiments on English, Spanish, and Korean language pairs demonstrate that our approach substantially improves speech overlap—achieving up to 24% relative gains compared to translations without explicit length constraints—while maintaining competitive translation quality measured by COMET scores. Furthermore, our framework does not require language-specific tuning, ensuring practicality for multilingual dubbing scenarios.

End-to-End Multilingual Automatic Dubbing via Duration-based Translation with Large Language Models

We present a synthetic data generation tool integrated into EvalAssist. EvalAssist is a web-based application designed to assist human-centered evaluation of language model outputs by allowing users to refine LLM-as-a-Judge evaluation criteria. The synthetic data generation tool in EvalAssist is tailored for evaluation contexts and informed by findings from user studies with AI practitioners. Participants identified key pain points in current workflows including circularity risks (where models are judged by criteria derived by themselves), compounded bias (amplification of biases across multiple stages of a pipeline), and poor support for edge cases, and expressed a strong preference for real-world grounding and fine-grained control. In response, our tool supports flexible prompting, RAG-based grounding, persona diversity, and iterative generation workflows. We also incorporate features for quality assurance and edge case discovery.

Synthetic Data for Evaluation: Supporting LLM-as-a-Judge Workflows with EvalAssist

Large language models (LLMs) are being increasingly used for planning in orchestrated multi-agent systems. However, existing LLM-based approaches often fall short of human expectations and, critically, lack effective mechanisms for users to inspect, understand, and control their behaviors. These limitations call for enhanced transparency, controllability, and human oversight. To address this, we introduce AIPOM, a system supporting human-in-the-loop planning through conversational and graph-based interfaces. AIPOM enables users to transparently inspect, refine, and collaboratively guide LLM-generated plans, significantly enhancing user control and trust in multi-agent workflows. Our code and demo video are available at https://github.com/megagonlabs/aipom.

AIPOM: Agent-aware Interactive Planning for Multi-Agent Systems

We present Marcel, a lightweight and open-source conversational agent designed to support prospective students with admission-related inquiries. The system aims to provide fast and personalized responses, while reducing workload of university staff. We employ retrieval-augmented generation to ground answers in university resources and to provide users with verifiable, contextually relevant information. To improve retrieval quality, we introduce an FAQ retriever that maps user questions to knowledge-base entries, allowing administrators to steer retrieval, and improving over standard dense/hybrid retrieval strategies. The system is engineered for easy deployment in resource-constrained academic settings. We detail the system architecture, provide a technical evaluation of its components, and report insights from a real-world deployment.

Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support

We introduce LLMtimesMapReduce-V3, a hierarchically modular agent system designed for long-form survey generation. Building on the prior work, LLMtimesMapReduce-V2, this version incorporates a multi-agent architecture where individual functional components, such as skeleton initialization, digest construction, and skeleton refinement, are implemented as independent model-context-protocol (MCP) servers. These atomic servers can be aggregated into higher-level servers, creating a hierarchically structured system. A high-level planner agent dynamically orchestrates the workflow by selecting appropriate modules based on their MCP tool descriptions and the execution history. This modular decomposition facilitates human-in-the-loop intervention, affording users greater control and customization over the research process. Through a multi-turn interaction, the system precisely captures the intended research perspectives to generate a comprehensive skeleton, which is then developed into an in-depth survey. \highlight{Human evaluations demonstrate that our system surpasses representative baselines in both content depth and length}, highlighting the strength of MCP-based modular planning. Demo, video and code are available at \url{https://github.com/thunlp/LLMxMapReduce}.

LLMtimesMapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System

Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications, from search and recommendation systems to generative tasks. Although scaling laws indicate that larger models generally yield better generalization and performance, their substantial computational requirements often render them impractical for many real-world scenarios at scale. In this paper, we present a comprehensive set of insights for training and deploying small language models (SLMs) that deliver high performance for a variety of industry use cases. We focus on two key techniques: (1) knowledge distillation and (2) model compression via pruning and quantization. These approaches enable SLMs to retain much of the quality of their larger counterparts while significantly reducing training/serving costs and latency. We detail the impact of these techniques on a variety of use cases in a large professional social network platform and share deployment lessons, including hardware optimization strategies that improve speed and throughput for both predictive and reasoning-based applications in Recommendation Systems.

Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems

Automatic prompt optimization (APO) uses algorithms to automatically refine prompts for LLMs, effectively reducing human effort in prompt engineering. However, applying APO to memory-enhanced conversational agents presents unique challenges. These agents leverage memory to retain information from historical interactions with users and provide context-aware and personalized responses. Optimizing prompts for these agents is challenging due to their complex, interconnected modules that include memory writing, reading, and response generation. This paper introduces a data-efficient framework for APO in these agents. Our approach leverages LLM to simultaneously optimize the prompts of all agents. We also introduce an automated evaluation module that not only provides a holistic quality score for responses but also performs error attribution, pinpointing failures within the specific modules. More importantly, to ensure the evaluation module aligns with human judgment, we develop a data-efficient active sampling algorithm with convex optimization to select the most informative samples for human feedback and prompt improvement. To our knowledge, this is the first work to establish automatic prompt optimization for memory-enhanced conversational agents, enabling efficient performance enhancement in real-world applications.

Downloads

Next from EMNLP 2025

Efficient Model Development through Fine-tuning Transfer

Similar lecture

Attention Head Masking for Inference Time Content Selection in Abstractive Summarization

.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

Efficient Model Development through Fine-tuning Transfer

Similar lecture

Attention Head Masking for Inference Time Content Selection in Abstractive Summarization

Downloads