United States

Large language models (LLMs) have become the norm in natural language processing (NLP), excelling in few-shot in-context learning (ICL) with their remarkable abilities. Nonetheless, the success of ICL largely hinges on the choice of few-shot demonstration examples, making the selection process increasingly crucial. Existing methods have delved into optimizing the quantity and semantic similarity of these examples to improve ICL performances. However, our preliminary experiments indicate that the effectiveness of ICL is limited by the length of the input context. Moreover, varying combinations of few-shot demonstration examples can significantly boost accuracy across different test samples. To address this, we propose a novel method named parallel in-context learning (ParaICL) that effectively utilizes all demonstration examples without exceeding the manageable input context length. ParaICL employs parallel batching to distribute demonstration examples into different batches according to the semantic similarities of the questions in the demonstrations to the test question. It then computes normalized batch semantic scores for each batch. A weighted average semantic objective, constrained by adaptive plausibility, is applied to select the most appropriate tokens. Through extensive experiments, we validate the effectiveness of ParaICL and conduct ablation studies to underscore its design rationale. We further demonstrate that ParaICL can seamlessly integrate with existing methods.

NAACL 2025

ParaICL: Towards Parallel In-Context Learning

efficient method

large language model

in-context learning

### 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 to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Current intent detection work experiments with minor intent categories. However, in real-world scenarios of data analysis dialogue systems, intents are composed of combinations of numerous metrics and dimensions, resulting in countless intents and posing challenges for the language model. The retrieval-augmented generation (RAG) method efficiently retrieves key intents. However, the single retrieval route sometimes fails to recall target intents and causes incorrect results. To alleviate the above challenges, we introduce the DSRAG framework combining query-to-query (Q2Q) and query-to-metadata (Q2M) double-stream RAG approaches. Specifically, we build a repository of query statements for Q2Q using the query templates with the key intents. When a user’s query comes, it rapidly matches repository statements. Once the relevant query is retrieved, the results can be quickly returned. In contrast, Q2M retrieves the relevant intents from the metadata and utilizes large language models to choose the answer. Experimental results show that DSRAG achieves significant improvements compared with merely using prompt engineering and a single retrieval route.

DSRAG: A Double-Stream Retrieval-Augmented Generation Framework for Countless Intent Detection

Unrestricted access to external Large Language Models (LLM) based services like ChatGPT and Gemini can lead to potential data leakages, especially for large enterprises providing products and services to clients that require legal confidentiality guarantees. However, a blanket restriction on such services is not ideal as these LLMs boost employee productivity. Our goal is to build a solution that enables enterprise employees to query such external LLMs, without leaking confidential internal and client information. In this paper, we propose QueryShield - a platform that enterprises can use to interact with external LLMs without leaking data through queries. It detects if a query leaks data, and rephrases it to minimize data leakage while limiting the impact to its semantics. We construct a dataset of 1500 queries and manually annotate them for their sensitivity labels and their low sensitivity rephrased versions. We fine-tune a set of lightweight model candidates using this dataset and evaluate them using multiple metrics including one we propose specific to this problem.

QueryShield: A Platform to Mitigate Enterprise Data Leakage in Queries to External LLMs

E-commerce live streaming in China, particularly on platforms like Douyin, has become a major sales channel, but hosts often use morphs to evade scrutiny and engage in false advertising. This study introduces the Live Auditory Morph Resolution (LiveAMR) task to detect such violations. Unlike previous morph research focused on text-based evasion in social media and underground industries, LiveAMR targets pronunciation-based evasion in health and medical live streams. We constructed the first LiveAMR dataset with 86,790 samples and developed a method to transform the task into a text-to-text generation problem. By leveraging large language models (LLMs) to generate additional training data, we improved performance and demonstrated that morph resolution significantly enhances live streaming regulation.

Chinese Morph Resolution in E-commerce Live Streaming Scenarios

The emergence of Large Language Models has created new opportunities for building agent applications across various domains with tools such as Langchain. To address the lack of targeted open benchmarks for agent frameworks, we designed a benchmark that features domain-specific, small knowledge bases, and includes a diverse set of questions categorized by type, such as simple, multi-hop, aggregation, and reasoning questions. We evaluated OpenAI's assistant API versus a RAG assistant built with Langchain. We also deployed a RAG system with insights from the benchmark as a pilot run over a two year span as a course assistant in a computer science course. We present insights from the benchmark evaluation and usage data for the community to develop better agents for various use cases.

Towards Reliable Agents: Benchmarking Customized LLM-Based Retrieval-Augmented Generation Frameworks with Deployment Validation

The growing adoption of large language models (LLMs) in business applications has amplified interest in Natural Language to SQL (NL2SQL) solutions, in which there is competing demand for high performance and efficiency. Domain- and customer-specific requirements further complicate the problem. To address this conundrum, we introduce Distill-C, a distilled customization framework tailored for NL2SQL tasks. Distill-C utilizes large teacher LLMs to produce high-quality synthetic data through a robust and scalable pipeline. Finetuning smaller and open-source LLMs on this synthesized data enables them to rival or outperform teacher models an order of magnitude larger. 
Evaluated on multiple challenging benchmarks, Distill-C achieves an average improvement of 36% in execution accuracy compared to the base models from three distinct LLM families. Additionally, on three internal customer benchmarks, Distill-C demonstrates a 22.6% performance improvement over the base models. Our results demonstrate that Distill-C is an effective, high-performing and generalizable approach for deploying lightweight yet powerful NL2SQL models, delivering exceptional accuracies while maintaining low computational cost.

Distill-C: Enhanced NL2SQL via Distilled Customization with LLMs

Maintaining persona consistency is paramount in the application of open-domain dialogue systems, as exemplified by models like ChatGPT. Despite significant advancements, the limited scale and diversity of current persona dialogue datasets remain challenges to achieving robust persona-consistent dialogue models. In this study, drawing inspiration from the success of large-scale pre-training, we introduce PPDS, an open-domain persona dialogue system that employs extensive generative pre-training on a persona dialogue dataset to enhance persona consistency. Specifically, we present a persona extraction model designed to autonomously and precisely generate vast persona dialogue datasets. Additionally, we unveil a pioneering persona augmentation technique to address the invalid persona bias inherent in the constructed dataset. Both quantitative and human evaluations consistently highlight the superior response quality and persona consistency of our proposed model, underscoring its effectiveness.

Dialogue Language Model with Large-Scale Persona Data Engineering

News aggregators play a key role in the rapidly evolving digital landscape by providing comprehensive and timely news stories aggregated from diverse sources into one feed. As these articles are sourced from different outlets, they often end up covering the same underlying event but differ in phrasing, formatting or supplemented with additional details. It is crucial for the news aggregators to identify these near-duplicates, improving the content quality and user engagement by steering away from redundant information. The problem of near-duplicate news detection has become harder with increasing use of paywalls by the news websites resulting in restricted access to the content. It is now common to get only the headline and a short snippet from the article. Previous works have concentrated on full length versions of documents such as webpages. There is very little work that focuses on this variation of the near-duplicate detection problem in which only headline and a small text blurb is available for each news article. We propose Near-Duplicate Detection Using Metadata Augmented Communities (NDD-MAC) approach that combines embeddings from pretrained language model (PLM) and latent metadata of a news article followed by community detection to identify clusters of near-duplicates. We show the efficacy of proposed approach using 2 different real-world datasets. By integrating metadata with community detection, NDD-MAC is able to detect nuanced similarities and differences in news snippets and offers an industrial scale solution for the near-duplicate detection in scenarios with restricted content availability.

Improved Near-Duplicate Detection for Aggregated and Paywalled News-Feeds

In human cognitive memory psychology, context-dependent effect helps retrieve key memory cues that is essential for recalling relevant knowledge in problem-solving. Inspired by this, we introduce the context-dependent memory framework (CDMem), an efficient architecture that mimics human memory processes through multistage encoding, context-aware storage, and retrieval strategies for LLM-centric agents.
We propose multistage memory encoding strategies for acquiring high-quality multi-level knowledge: expert encoding compresses raw trajectories from a domain-expert perspective, short-term encoding consolidates experiences from current tasks, and long-term encoding reflects insights from past tasks.
For memory storage and retrieval, we design a semi-structured, context-dependent indexing mechanism that allows agents to efficiently and accurately recall the most relevant multi-level knowledge, tailored to the current task and environmental context.
Furthermore, the proposed CDMem framework is an online learning architecture, enabling agents to efficiently learn and update memory while adapting to novel environments and tasks in real-world applications.
We conduct extensive experiments on two interactive decision-making benchmarks in the navigation and manipulation domain, ALFWorld and ScienceWorld. Using GPT-4o-mini, a more efficient variant of LLMs, our method surpasses state-of-the-art online LLM-centric approaches, achieving success rates of 85.8% and 56.0%, respectively.
We hope that this work will serve as a valuable reference for both academic and industrial communities in advancing agent-based applications.

An Efficient Context-Dependent Memory Framework for LLM-Centric Agents

Large language models (LLMs) have excelled in various NLP tasks, including machine translation (MT), yet most studies focus on sentence-level translation. This work investigates the inherent capability of instruction-tuned LLMs for document-level translation (docMT). Unlike prior approaches that require specialized techniques, we evaluate LLMs by directly prompting them to translate entire documents in a single pass. Our results show that this method improves translation quality compared to translating sentences separately, even without document-level fine-tuning. However, this advantage is not reflected in BLEU scores, which often favor sentence-based translations. We propose using the LLM-as-a-judge paradigm for evaluation, where GPT-4 is used to assess document coherence, accuracy, and fluency in a more nuanced way than n-gram-based metrics. Overall, our work demonstrates that instruction-tuned LLMs can effectively leverage document context for translation. However, we caution against using BLEU scores for evaluating docMT, as they often provide misleading outcomes, failing to capture the quality of document-level translation.

Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation

Vision-Language Models (VLMs) generate contextually rich text from visual data but are prone to "hallucinations"—content not supported by visuals. This undermines user trust and limits the applicability of VLMs in critical domains like healthcare and law, either by directly interacting with images or by accessing token probabilities assigned by vision-language models (VLMs). We propose a language-only black-box hallucination detection approach for VLMs. We evaluate three methods: (1) shallow classifiers using text statistics like TF-IDF and TTP, (2) transformer-based classifiers capturing semantic nuances, and (3) an ensemble model combining strengths of multiple architectures. By analyzing prompts and outputs, we identify patterns enabling classifiers to distinguish between supported and unsupported content. These findings show the effectiveness of language-only classifiers in detecting hallucinations and offer insights into the textual features aiding this process.

Downloads

Next from NAACL 2025

DSRAG: A Double-Stream Retrieval-Augmented Generation Framework for Countless Intent Detection

Similar lecture

Revisiting In-Context Learning with Long Context Language Models