China

Human fact-checking is too slow to meet current demands, making automatic fact-checking system an essential alternative. Evaluating such systems is challenging as existing benchmark datasets either suffer from leakage or evidence incompleteness. This limits the realism of current evaluations. We present textbfPoliti-Fact-Only (PFO), a 5-class benchmark dataset of 2,982 political claims from politifact.com, where all post-claim analysis and annotator cues have been removed manually from evidence article. After filtration, evidence contains information available prior to the claim’s verification. By evaluating PFO, we see an average performance drop of textbf11.39\% in terms of macro-f1 compared to PFO&#39;s unfiltered version. Based on the identified challenges of the existing LLM-based fact-checking system, we propose textbfRAV (Recon-Answer-Verify), an agentic framework with three agents, it iteratively generates and answers sub-questions to verify different aspects of the claim before finally generating the label. Unlike prior literature, we worked on reducing the follow-up question complexity by leveraging two 2 types of structured questions, which either validate a fact or inquire about a fact. RAV generalizes across both domains and label granularities, outperforming state-of-the-art methods by textbf57.5\% on PFO textit(political, 5-class) and by textbf3.05\% on the widely used HOVER dataset textit(encyclopedic, 2-class).

EMNLP 2025

Recon, Answer, Verify: Agents in Search of Truth

llm/ai agents

misinformation detection

question generation

fact checking

reasoning

## Welcome to EMNLP 2022!
I am delighted to welcome you to EMNLP 2022! I believe this conference has been complicated beyond any precedent. Over the past year, it’s been thrilling to see the organization team approach each new puzzle with creativity and enthusiasm. We hope that those participating in Abu Dhabi as well as those joining remotely will leave the conference feeling newly inspired by the program and newly connected to our ever-growing community. Following EMNLP 2021 and major NLP conferences since, EMNLP 2022 is “hybrid,” serving both virtual and in-person participants.

Our key innovations for EMNLP 2022 include:

* EMNLP 2022 is “hybrid” in a second sense, as well: we allowed both direct and rolling review paper submissions, building on the pilot experiment of EMNLP 2021, which considered a small number of ARR submissions. 
* Familiar from NAACL but new to EMNLP, we’ve added an industry track.
* During the conference, “portals” will link virtual poster sessions to in-person conference participants during poster sessions each day.
* The first ACL-family conference in the United Arab Emirates.

 *Message from Noah A. Smith, University of Washington and Allen Institute for AI, Seattle, Washington, USA* 
***EMNLP 2022 General Chair***
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/9eec7d4a287ee18c278b08229290aa83.png)](https://drive.google.com/file/d/1OlPv6QBeo62VVTughj2jkiLeyHd1WnUt/view)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/a3db7a768409f05192210d98601edb25.png)](https://emnlp2022.rocket.chat/)

To access this site you need to register. Please register [here](https://2022.emnlp.org/registration/).

Register here

EMNLP 2022

Welcome!
EMNLP 2022 will take place in Abu Dhabi from December 7th to December 11th, 2022. And it will be held in hybrid mode, both online and offline.

Human fact-checking is too slow to meet current demands, making automatic fact-checking system an essential alternative. Evaluating such systems is challenging as existing benchmark datasets either suffer from leakage or evidence incompleteness. This limits the realism of current evaluations. We present textbfPoliti-Fact-Only (PFO), a 5-class benchmark dataset of 2,982 political claims from politifact.com, where all post-claim analysis and annotator cues have been removed manually from evidence article. After filtration, evidence contains information available prior to the claim’s verification. By evaluating PFO, we see an average performance drop of textbf11.39\% in terms of macro-f1 compared to PFO's unfiltered version. Based on the identified challenges of the existing LLM-based fact-checking system, we propose textbfRAV (Recon-Answer-Verify), an agentic framework with three agents, it iteratively generates and answers sub-questions to verify different aspects of the claim before finally generating the label. Unlike prior literature, we worked on reducing the follow-up question complexity by leveraging two 2 types of structured questions, which either validate a fact or inquire about a fact. RAV generalizes across both domains and label granularities, outperforming state-of-the-art methods by textbf57.5\% on PFO textit(political, 5-class) and by textbf3.05\% on the widely used HOVER dataset textit(encyclopedic, 2-class).

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.

Large language models (LLMs) have achieved overwhelming success but require massive storage and computational resources to support the generative inference. Post-training quantization (PTQ) is a promising approach to reduce memory usage, latency and energy consumption of the deployment of LLMs. However, the presence of outliers makes most existing PTQ methods dedicated to dynamic quantization, which turns out hardware-unfriendly and often leads to large quantization errors in static scenarios. To address the above limitations, we introduce a Static Hierarchical Mix-precision Quantization method (SHMQ), which enables near-lossless and hardware-friendly compression of LLMs. Theoretically, our proposed SHMQ quantifies both inter-layer and intra-layer sensitivity through unified derivations involving Hessian. Specifically, SHMQ conducts a systematic precision allocation strategy, which seamlessly integrates coarse-grained inter-layer and fine-grained intra-layer static mix-precision quantization. Furthermore, the permutation procedure, which reorders sensitive channels and insensitive channels that share similar distribution, is leveraged to mitigate static quantization error. Our proposed SHMQ achieves 75.58\% on zero-shot reasoning tasks in W4.8A8 Qwen2.5-7B-Instruct, narrowing the accuracy gap to merely 0.13\% while yielding averaged 2.86times practical speedup.

Beyond Dynamic Quantization: An Efficient Static Hierarchical Mix-precision Framework for Near-Lossless LLM Compression

We assess whether AI systems can credibly evaluate investment risk appetite—a task that must be thoroughly validated before automation. Our analysis was conducted on proprietary systems (GPT, Claude, Gemini) and open-weight models (LLaMA, DeepSeek, Mistral), using carefully curated user profiles that reflect real users with varying attributes such as country and gender. As a result, the models exhibit significant variance in score distributions when user attributes—such as country or gender—that should not influence risk computation are changed. For example, GPT-4o assigns higher risk scores to Nigerian and Indonesian profiles. While some models align closely with expected scores in the low- and mid-risk ranges, none maintain consistent scores across regions and demographics, thereby violating AI and finance regulations.

Evaluating AI for Finance: Is AI Credible at Assessing Investment Risk Appetite?

Training large language models at scale suffers from costly instabilities. We introduce the R-Metric, a proactive reliability metric that predicts failures before they occur by combining hardware monitoring, training dynamics, and model performance. Achieving 0.973-1.00 F1-Score with 12-minute lead time, our lightweight approach (1.8% overhead) democratizes enterprise-grade reliability monitoring for resource-constrained organizations.

A Proactive Reliability Metric for Detecting Failures in Language Model Training

Large language models (LLMs) acquire general linguistic knowledge from massive-scale pretraining. However, pretraining data mainly comprised of web-crawled texts contain undesirable social biases which can be perpetuated or even amplified by LLMs. In this study, we propose an efficient yet effective annotation pipeline to investigate social biases in the pretraining corpora. Our pipeline consists of protected attribute detection to identify diverse demographics, followed by regard classification to analyze the language polarity towards each attribute. Through our experiments, we demonstrate the effect of our bias analysis and mitigation measures, focusing on Common Crawl as the most representative pretraining corpus.

Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification

People increasingly seek healthcare information from Large Language Models (LLMs), yet the nature of these conversational interactions and their inherent risks remain largely unexplored. In this paper, we filter large-scale conversational AI datasets to achieve HealthChat-14K, a curated dataset of 14K real-world conversations composed of 62K user messages. We use HealthChat-14K and a clinician-driven taxonomy for how users interact with LLMs when seeking healthcare information in order to systematically study users' conversational trajectories, interaction patterns, emotional behaviors, and sycophancy-inducing interactions. Our analysis reveals insights into how users seek healthcare information, including the nature of health information users seek, their typical conversational trajectories, expressions of affect, and specific interaction patterns related to conversational challenges and leading questions, underscoring the need for improvements in the healthcare support capabilities of LLMs deployed as conversational AI. We will release our analyzed conversations and corresponding analysis artifacts in a curated dataset to foster future research.

What's Up, Doc?: Analyzing How Users Seek Health Information in Large-Scale Conversational AI Datasets

Sentiment analysis of historical literature provides valuable insights for humanities research, yet remains challenging due to scarce annotations and limited generalization of models trained on modern texts. Prior work has primarily focused on two directions: using sentiment lexicons or leveraging large language models (LLMs) for annotation. However, lexicons are often unavailable for historical texts due to limited linguistic resources, and LLM-generated labels often reflect modern sentiment norms and fail to capture the implicit, ironic, or morally nuanced expressions typical of historical literature, resulting in noisy supervision. To address these issues, we introduce a role-guided annotation strategy that prompts LLMs to simulate historically situated perspectives when labeling sentiment. Furthermore, we design a prototype-aligned framework that learns sentiment prototypes from high-resource data and aligns them with low-resource representations via symmetric contrastive loss, improving robustness to noisy labels. Experiments across multiple historical literature datasets show that our method outperforms state-of-the-art baselines, demonstrating its effectiveness.

Role-Guided Annotation and Prototype-Aligned Representation Learning for Historical Literature Sentiment Classification

Contextual biasing in ASR systems is critical for recognizing rare, domain-specific terms but becomes impractical with large keyword dictionaries due to prompt size and latency constraints. We present RECAST--a lightweight retrieval-augmented approach that repurposes decoder states of a pretrained ASR model to retrieve relevant keywords without requiring audio exemplars. RECAST introduces a contrastively trained retriever that aligns decoder-state embeddings with textual keyword representations, enabling fast token-level retrieval over large dictionaries. Retrieved keywords are ranked and formatted into a prompt to guide a downstream speech language model. Trained solely on LibriSpeech and evaluated on out-of-domain benchmarks covering up to 4,000 keywords across diverse domains, RECAST consistently outperforms full-list prompt biasing and strong phonetic/text baselines. It achieves up to 54.3% relative reduction in entity WER and 41.3% overall WER improvement over the baseline, along with up to 2.5x higher recall in challenging settings. Furthermore, RECAST remains effective for diverse languages such as Hindi, demonstrating its scalability, language-agnostic design, and practicality for real-world contextual ASR.

RECAST: Retrieval-Augmented Contextual ASR via Decoder-State Keyword Spotting

While Vision-Language Models (VLMs) have achieved competitive performance in various tasks, their comprehension of the underlying structure and semantics of a scene remains understudied. To investigate the understanding of VLMs, we study their capability regarding object properties and relations in a controlled and interpretable manner. To this scope, we introduce CIVET, a novel and extensible framework for systemati**C** evaluat**I**on **V**ia controll**E**d s**T**imuli. CIVET addresses the lack of standardized systematic evaluation for assessing VLMs' understanding, enabling researchers to test hypotheses with statistical rigor. With CIVET, we evaluate five state-of-the-art VLMs on exhaustive sets of stimuli, free from annotation noise, dataset-specific biases, and uncontrolled scene complexity. Our findings reveal that 1) current VLMs can accurately recognize only a limited set of basic object properties; 2) their performance heavily depends on the position of the object in the scene; 3) they struggle to understand basic relations among objects. Furthermore, a comparative evaluation with human annotators reveals that VLMs still fall short of achieving human-level accuracy.

CIVET: Systematic Evaluation of Understanding in VLMs

We propose a training-free approach to improve sentence embeddings leveraging test-time compute by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic training data, our approach does not require access to model parameters or the computational resources typically required for fine-tuning state-of-the-art models. Generatively Augmented Sentence Encoding variates the input text by paraphrasing, summarising, or extracting keywords, followed by pooling the original and synthetic embeddings. Experimental results on the Massive Text Embedding Benchmark for Semantic Textual Similarity (STS) demonstrate performance improvements across a range of embedding models using different generative models for augmentation. We find that generative augmentation leads to larger performance improvements for embedding models with lower baseline performance. These findings suggest that integrating generative augmentation at inference time adds semantic diversity and can enhance the robustness and generalisability of sentence embeddings for embedding models. Our results show that performance gains depend on the embedding model and the dataset.

GASE: Generatively Augmented Sentence Encoding

The generative large language models (LLMs) are increasingly used for data augmentation tasks, where text samples are paraphrased (or generated anew) and then used for downstream model fine-tuning. This is useful, especially for low-resource settings. For better augmentations, LLMs are prompted with examples (few-shot scenarios). Yet, the samples are mostly selected randomly, and a comprehensive overview of the effects of other (more ''informed'') sample selection strategies is lacking. In this work, we compare sample selection strategies existing in the few-shot learning literature and investigate their effects in LLM-based textual augmentation in a low-resource setting. We evaluate this on in-distribution and out-of-distribution model performance. Results indicate that while some ''informed'' selection strategies increase the performance of models, especially for out-of-distribution data, it happens only seldom and with marginal performance increases. Unless further advances are made, a default of random sample selection remains a good option for augmentation practitioners.

Downloads

Next from EMNLP 2025

Beyond Dynamic Quantization: An Efficient Static Hierarchical Mix-precision Framework for Near-Lossless LLM Compression

Similar lecture

Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation

.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

Beyond Dynamic Quantization: An Efficient Static Hierarchical Mix-precision Framework for Near-Lossless LLM Compression

Similar lecture

Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation

Downloads