China

Disinformation is among the top risks of generative artificial intelligence (AI) misuse. Global adoption of generative AI necessitates red-teaming evaluations (i.e., systematic adversarial probing) that are robust across diverse languages and cultures, but red-teaming datasets are commonly US- and English-centric. To address this gap, we propose &#39;&#39;anecdoctoring&#39;&#39;, a novel red-teaming approach that automatically generates adversarial prompts across languages and cultures. We collect misinformation claims from fact-checking websites in three languages (English, Spanish, and Hindi) and two geographies (US and India). We then cluster individual claims into broader narratives and characterize the resulting clusters with knowledge graphs, with which we augment an attacker LLM. Our method produces higher attack success rates and offers interpretability benefits relative to few-shot prompting. Results underscore the need for disinformation mitigations that scale globally and are grounded in real-world adversarial misuse.

EMNLP 2025

Anecdoctoring: Automated Red-Teaming Across Language and Place

red teaming

llms

disinformation

### 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!

NAACL 2025

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

Disinformation is among the top risks of generative artificial intelligence (AI) misuse. Global adoption of generative AI necessitates red-teaming evaluations (i.e., systematic adversarial probing) that are robust across diverse languages and cultures, but red-teaming datasets are commonly US- and English-centric. To address this gap, we propose ''anecdoctoring'', a novel red-teaming approach that automatically generates adversarial prompts across languages and cultures. We collect misinformation claims from fact-checking websites in three languages (English, Spanish, and Hindi) and two geographies (US and India). We then cluster individual claims into broader narratives and characterize the resulting clusters with knowledge graphs, with which we augment an attacker LLM. Our method produces higher attack success rates and offers interpretability benefits relative to few-shot prompting. Results underscore the need for disinformation mitigations that scale globally and are grounded in real-world adversarial misuse.

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.

Process-supervised reward models (PRMs) excel at providing step-by-step verification for large language model (LLM) outputs in domains like mathematics and coding. However, their application to fields lacking ground-truth answers, such as clinical note generation, poses significant challenges. We introduce a novel framework for training PRMs to deliver step-level reward signals for LLM-generated clinical notes. By precisely defining meaningful "steps," injecting realistic "errors" informed by domain expertise, and leveraging LLMs to generate process supervision data at scale, we overcome previous limitations. Our PRM, built on LLaMA-3.1 8B, consistently outperforms proprietary reasoning and non-reasoning models, achieving state-of-the-art performance on two key evaluations: (1) distinguishing gold-standard from error-containing samples with 98.8% accuracy, and (2) selecting physician-preferred clinical notes with 56.2% accuracy. We investigate critical components for effective PRM training, including optimal loss functions and data selection strategies, and present a comprehensive physician reader study identifying predictors of downstream Best-of-N performance. Our study sheds light on unlocking the potential of PRMs for diverse generative tasks across domains.

Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise

Speculative decoding is a prominent technique for accelerating LLM inference by leveraging an auxiliary draft model, but its effectiveness is limited by the autoregressive nature of draft generation, where acceptance rates depend on the draft model’s size. Scaling the draft model improves acceptance but also increases speculation latency, limiting overall speedup. Furthermore, fine-tuning both the draft and target models is often necessary to achieve high acceptance rates, adding complexity to inference systems as the number of downstream tasks grows. Single-model approaches like Medusa generate speculative tokens non-autoregressively but lack token dependencies, limiting effectiveness. Alternatives like Hydra and Eagle incorporate token dependencies but rely on dedicated heads, making speculation independent of the base model and limiting the extent to which stronger base models can improve speculation. We introduce a novel speculative decoding method that integrates speculative draft generation directly within the target model using multi-stream attention. This improves acceptance rates by introducing interdependencies between speculative tokens while ensuring non-autoregressive draft generation with minimal overhead. As target models scale in size and quality, speculative generation improves naturally with our method, unlike prior approaches. Furthermore, our approach is both parameter- and FLOP-efficient, requiring over 1000X fewer additional parameters than Medusa, making it highly suitable for resource-constrained devices. We design our method to operate in two modes: (1) Lossless mode, a plug-and-play method that preserves the output of any pre-trained model; and (2) Shared mode, optimizing both speedup and downstream performance. We demonstrate a 2–3.5X speedup across diverse tasks, including summarization, translation, question answering, mathematical reasoning, SQL generation, and retrieval-augmented generation (RAG).

Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention

Poetry is an expressive form of art that invites multiple interpretations, as readers often bring their own emotions, experiences, and cultural backgrounds into their understanding of a poem. Recognizing this, we aim to generate images for poems and improve these images in a zero-shot setting, enabling audiences to modify images as per their requirements. To achieve this, we introduce a novel textitWeighted Prompt Manipulation (WPM) technique, which systematically modifies attention weights and text embeddings within diffusion models. By dynamically adjusting the importance of specific words, textitWPM enhances or suppresses their influence in the final generated image, leading to semantically richer and more contextually accurate visualizations. Our approach exploits diffusion models and large language models (LLMs) such as GPT in conjunction with existing poetry datasets, ensuring a comprehensive and structured methodology for improved image generation in the literary domain. To the best of our knowledge, this is the first attempt at integrating weighted prompt manipulation for enhancing imagery in poetic language.

Do It Yourself (DIY): Modifying Images for Poems in a Zero-Shot Setting Using Weighted Prompt Manipulation

Agentic Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by enabling dynamic, multi-step reasoning and information retrieval. However, these systems often exhibit sub-optimal search behaviors like over-search (retrieving redundant information) and under-search (failing to retrieve necessary information), which hinder efficiency and reliability. This work formally defines and quantifies these behaviors, revealing their prevalence across multiple QA datasets and agentic RAG systems (e.g., one model could have avoided searching in 27.7% of its search steps). Furthermore, we demonstrate a crucial link between these inefficiencies and the models’ uncertainty regarding their own knowledge boundaries, where response accuracy correlates with model’s uncertainty in its search decisions. To address this, we propose β-GRPO, a reinforcement learning-based training method that incorporates confidence threshold to reward high-certainty search decisions. Experiments on seven QA benchmarks show that β-GRPO enable a 3B model with better agentic RAG ability, outperforming other strong baselines with a 4% higher average exact match score.

Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty

Incorporating external context can significantly enhance the response quality of Large Language Models (LLMs). However, real-world contexts often mix relevant information with disproportionate inappropriate content, posing reliability risks. How do LLMs process and prioritize mixed context? To study this, we introduce the Poisoned Context Testbed, pairing queries with real-world contexts containing relevant and inappropriate content. Inspired by associative learning in animals, we adapt the Rescorla-Wagner (RW) model from neuroscience to quantify how competing contextual signals influence LLM outputs. Our adapted model reveals a consistent behavioral pattern: LLMs exhibit a strong tendency to incorporate information that is less prevalent in the context. This susceptibility is harmful in real-world settings, where small amounts of inappropriate content can substantially degrade response quality. Empirical evaluations on our testbed further confirm this vulnerability. To tackle this, we introduce RW-Steering, a two-stage finetuning-based approach that enables the model to internally identify and ignore inappropriate signals. Unlike prior methods that rely on extensive supervision across diverse context mixtures, RW-Steering generalizes robustly across varying proportions of inappropriate content. Experiments show that our best fine-tuned model improves response quality by 39.8% and reverses the undesirable behavior curve, establishing RW-Steering as a robust, generalizable solution for improving LLM safety in real-world use.

Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context

This paper makes three contributions. First, via a substantial corpus of 1,419,047 comments posted on 3,161 YouTube news videos of major US cable news outlets, we analyze how users engage with LGBTQ+ news content. Our analyses focus both on positive and negative content. In particular, we construct a \textit{hope speech} classifier that detects positive (\textit{hope speech}), negative, neutral, and irrelevant content. Second, in consultation with a public health expert specializing on LGBTQ+ health, we conduct an annotation study with a balanced and diverse political representation and release a dataset of 3,750 instances with crowd-sourced labels and detailed annotator demographic information. Finally, beyond providing a vital resource for the LGBTQ+ community, our annotation study and subsequent in-the-wild assessments reveal (1) strong association between rater political beliefs and how they rate content relevant to a marginalized community, (2) models trained on individual political beliefs exhibit considerable in-the-wild disagreement, and (3) zero-shot large language models (LLMs) align more with liberal raters.

Hope vs. Hate: Understanding User Interactions with LGBTQ+ News Content in Mainstream US News Media through the Lens of Hope Speech

The effectiveness of in-context learning relies heavily on selecting demonstrations that provide all the necessary information for a given test input. To achieve this, it is crucial to identify and cover fine-grained knowledge requirements. However, prior methods often retrieve demonstrations based solely on embedding similarity or generation probability, resulting in irrelevant or redundant examples. In this paper, we propose **TopicK**, a topic coverage-based retrieval framework that selects demonstrations to comprehensively cover topic-level knowledge relevant to both the test input and the model. Specifically, TopicK estimates the topics required by the input and assesses the model’s knowledge on those topics. TopicK then iteratively selects demonstrations that introduce previously uncovered required topics, in which the model exhibits low topical knowledge. We validate the effectiveness of TopicK through extensive experiments across various datasets and both open- and closed-source LLMs. Our source code is available at https://anonymous.4open.science/r/TopicK_ARRmay

Topic Coverage-based Demonstration Retrieval for In-Context Learning

Large language models (LLMs) have achieved remarkable multi-step reasoning capabilities across various domains. However, LLMs still face distinct challenges in complex logical reasoning, as (1) proof-finding requires systematic exploration and the maintenance of logical coherence and (2) searching the right combination of premises at each reasoning step is inherently challenging in tasks with large premise space. To address this, we propose LogicTree, an inference-time modular framework employing algorithm-guided search to automate structured proof exploration and ensure logical coherence. Advancing beyond tree-of-thought (ToT), we incorporate caching mechanism into LogicTree to enable effective utilization of historical knowledge, preventing reasoning stagnation and minimizing redundancy. Furthermore, we address the combinatorial complexity of premise search by decomposing it into a linear process. The refined premise selection restricts subsequent inference to at most one derivation per step, enhancing reasoning granularity and enforcing strict step-by-step reasoning. Additionally, we introduce two LLM-free heuristics for premise prioritization, enabling strategic proof search. Experimental results on five datasets demonstrate that LogicTree optimally scales inference-time computation to achieve higher proof accuracy, surpassing chain-of-thought (CoT) and ToT with average gains of 23.6% and 12.5%, respectively, on GPT-4o. Moreover, within LogicTree, GPT-4o outperforms o3-mini by 7.6% on average.

LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models

Large Language Models (LLMs) have demonstrated impressive reasoning abilities, but their generated rationales often suffer from issues such as reasoning inconsistency and factual errors, undermining their reliability. Prior work has explored improving rationale quality via multi-reward fine-tuning or reinforcement learning (RL), where models are optimized for diverse objectives. While effective, these approaches train the model in a fixed manner and do not have any inference-time adaptability, nor can they generalize reasoning requirements for new test-time inputs. Another approach is to train specialized reasoning experts using reward signals and use them to improve generation at inference time. Existing methods in this paradigm are limited to using only a single expert and cannot improve upon multiple reasoning aspects. To address this, we propose MIXIE, a novel inference-time expert-mixing framework that dynamically determines mixing proportions for each expert, enabling contextualized and flexible fusion. We demonstrate the effectiveness of MIXIE on improving chain-of-thought reasoning in LLMs by merging commonsense and entailment reasoning experts finetuned on reward-filtered data. Our approach outperforms existing baselines on three question-answering datasets: StrategyQA, CommonsenseQA, and ARC, highlighting its potential to enhance LLM reasoning with efficient, adaptable expert integration.

Mixing Inference-time Experts for Enhancing LLM Reasoning

Retrieval-augmented generation (RAG) systems empower large language models (LLMs) to access external knowledge during inference. Recent advances have enabled LLMs to act as search agents via reinforcement learning (RL), improving information acquisition through multi-turn interactions with retrieval engines. However, existing approaches either optimize retrieval using search-only metrics (e.g., NDCG) that ignore downstream utility or fine-tune the entire LLM to jointly reason and retrieve—entangling retrieval with generation and limiting the real search utility and compatibility with frozen or proprietary models. In this work, we propose **s3**, a lightweight, model-agnostic framework that decouples the searcher from the generator and trains the searcher using a Gain Beyond RAG reward: the improvement in generation accuracy over naïve RAG. **s3** requires only 2.4k training samples to outperform baselines trained on over 70 times more data, consistently delivering stronger downstream performance across six general QA and five medical QA benchmarks.

Downloads

Next from EMNLP 2025

Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise

Similar lecture

Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models