China

Large language models (LLMs) often mislead users with confident hallucinations. Current approaches to detect hallucination require many samples from the LLM generator, which is computationally infeasible as frontier model sizes and generation lengths continue to grow. We present a remarkably simple baseline for detecting hallucinations in long-form LLM generations, with performance comparable to expensive multi-sample approaches while drawing only a single sample from the LLM generator. Our key observation is that LLM hidden states are highly predictive of long-form factuality and that this information may be efficiently extracted at inference time using a lightweight probe. We benchmark a variety of long-form hallucination detection methods across open-source models up to 405B parameters and demonstrate that our approach achieves competitive performance with up to 100x fewer FLOPs. Furthermore, our probes generalize to out-of-distribution model outputs, evaluated using hidden states of smaller open-source models. Our results demonstrate the promise of hidden state probes in detecting long-form LLM hallucinations.

EMNLP 2025

Simple Factuality Probes Detect Hallucinations in Long-Form Natural Language Generation

latent-space probes

hallucination detection

cost-effective

## Welcome to 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics!
This year, the conference is in Mexico City. NAACL was actually already planned for Mexico City in 2021, but due to the pandemic the entire conference was moved online. This year, finally, we get to go! So it is my sincere pleasure to welcome you to Mexico City, whether in person or virtually. Having the conference in Mexico City is a good opportunity to emphasize that NAACL is our flagship conference for ACL members not only in North America but also in Central and South America, even though NAACL has been bearing “North” in its name. At this year’s conference, we have a theme to match, with a theme track on the Languages of Latin America to showcase the linguistic diversity of the region.
 
The opportunity to present at NAACL should not depend on a researcher’s travel budget, or their family status. This is why it is so important to make virtual participation at NAACL as good an experience as possible – but we want to also provide a good experience for in-person participants. As a community, we are still working out the best way to do that. This year at NAACL, we are trying out a big virtual poster session ahead of the conference, with the hope that this will make make for a lively and interactive experience. At the same time, we are reducing virtual oral presentations, which seem to be particularly tricky to make to work well. A big thanks to the NAACL program chairs and to Luciana Benotti for all their ideas and work to improve the virtual experience. And participants, virtual as well as in-person: Please let us know what worked for you and what didn’t, so we can continue to improve hybrid conferences. 
 
I have been lucky to work with many amazing people. Without their insight, dedication and patience, and without the many hours of work they put in, NAACL would not have been possible. A huge thank you to the program chairs Helena Gomez, Kevin Duh, and Steve Bethard – you are the best! 
 
Finally, I would like to thank all authors, invited speakers and panelists, area chairs and reviewers, the volunteers organizing and chairing sessions, and all attendees, in-person and virtual. Thank you for helping us make NAACL 2024 come to life. 
 
Welcome and hope you all enjoy the conference! 
Katrin Erk 
The University of Texas at Austin 
NAACL-2024 General Chair 
*You can read the full Welcome message in the [Conference Handbook (downloadable)](https://drive.google.com/file/d/1H1NvW0VASQjkSCYgw3mr-3l4yYDSxz6B/view?usp=sharing)*

To access the event page you need to register [**here.**](http://acl.swoogo.com/naacl2024) 
Your access to the event page is limited based on your registration type. If you registered for workshops only, you will gain access to full workshops content on the day of the workshops program.

Please register!

NAACL 2024

2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics

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.

Sequential Recommendation Systems (SRS) have become essential in many real-world applications. However, existing SRS methods often rely on collaborative filtering signals and fail to capture real-time user preferences, while Conversational Recommendation Systems (CRS) excel at eliciting immediate interests through natural language interactions but neglect historical behavior. To bridge this gap, we propose CESRec, a novel framework that integrates the long-term preference modeling of SRS with the real-time preference elicitation of CRS. We introduce semantic-based pseudo interaction construction, which dynamically updates users’ historical interaction sequences by analyzing conversational feedback, generating a pseudo-interaction sequence that seamlessly combines long-term and real-time preferences. Additionally, we reduce the impact of outliers in historical items that deviate from users’ core preferences by proposing dual alignment outlier items masking, which identifies and masks such items using semantic-collaborative aligned representations. Extensive experiments demonstrate that CESRec achieves state-of-the-art performance by boosting strong SRS models, validating its effectiveness in integrating conversational feedback into SRS.

CESRec: Constructing Pseudo Interactions for Sequential Recommendation via Conversational Feedback

Large language models have consistently struggled with complex reasoning tasks, such as mathematical problem-solving. Investigating the internal reasoning mechanisms of these models can help us design better model architectures and training strategies, ultimately enhancing their reasoning capability. In this study, we constructed a symbolic multi-step reasoning task to investigate the information propagation mechanisms in Transformer models when solving the task through direct answering and Chain-of-Thought (CoT) reasoning. We introduced the concept of buffer mechanism: the model stores various information in distinct buffers and selectively extracts it through the query-key matrix. We proposed a random matrix-based algorithm to enhance the model's reasoning ability. This algorithm introduces only 132 trainable parameters, yet leads to significant performance improvements on 7 multi-step reasoning datasets, including PrOntoQA, LogicAsker, and LogicInference. These findings provide new insights into understanding the large language models.

Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism

Existing alignment methods for preference optimization of large language models (LLMs) aim to enhance model performance by utilizing pairs of positive and negative samples. However, due to the limited capacity of models in scoring or generating responses, the quality of positive and negative samples may become similar during training, which complicates optimization for preference learning. To address this issue, we introduce SeaPO, a Strategic Error Amplification method that leverages multiple error types to introduce specific error patterns into the model Preference Optimization. This strategy ensures that negative samples are more erroneous than positive samples and preference-based training is employed to mitigate the occurrence of these errors, thereby enhancing model performance. Evaluations across five capability dimensions and different model scales (1.5B to 14B) demonstrate that the generated data significantly improved overall model performance, particularly in terms of truthfulness, with improvements of 5–10 percentage points observed. Further analysis reveals that task performance varies depending on the error types introduced. Injecting the most common error types improves performance in related tasks, while a mix of error types leads to a broader performance enhancement: most tasks show stable improvements, while a few tasks exhibit significant gains. The code and scripts are as follows: https://anonymous.4open.science/r/SeaPO-4002.

SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models

Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models. While some existing methods attempt to restore safety by incorporating additional safety data, the quality of such data typically falls short of that used in the original alignment process. Moreover, these high-quality safety datasets are generally inaccessible, making it difficult to fully recover the model's original safety. We ask: How can we preserve safety while improving downstream task performance without additional safety data? We show that simply merging the weights of pre- and post-fine-tuned models effectively mitigates safety degradation while enhancing performance. Experiments across different downstream tasks and models validate the method’s practicality and effectiveness.

Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging

Recent advances in chain-of-thought (CoT) prompting have demonstrated the ability of large language models (LLMs) to perform multi-step reasoning. While prior work focuses on improving CoT generation quality or attributing token-level importance, we propose a novel framework to structurally analyze the latent dynamics of CoT trajectories for interpretability. Our method segments generated CoT into discrete reasoning steps, abstracts each step into a spectral embedding based on the eigenvalues of token-level Gram matrices, and clusters these embeddings into semantically meaningful latent states. We model the global evolution of reasoning as a first-order Markov chain over latent clusters, yielding interpretable transition structures. Through t-SNE visualizations and Monte Carlo rollouts, we uncover consistent trajectories across tasks and models, supporting the hypothesis that LLM reasoning follows globally coherent yet abstract paths.

Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics

While Reinforcement Learning from Human Feedback (RLHF) is widely used to align Large Language Models (LLMs) with human preferences, it typically assumes homogeneous preferences across users, overlooking diverse human values and minority viewpoints. Although personalized preference learning addresses this by tailoring separate preferences for individual users, the field lacks standardized methods to assess its effectiveness. We present a multi-faceted evaluation framework that measures not only performance but also fairness, unintended effects, and adaptability across varying levels of preference divergence. Through extensive experiments comparing eight personalization methods across three preference datasets, we demonstrate that performance differences between methods could reach 36% when users strongly disagree, and personalization can introduce up to 20% safety misalignment. These findings highlight the critical need for holistic evaluation approaches to advance the development of more effective and inclusive preference learning systems.

When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning

In modern dialogue systems, the ability to implicitly infer user backgrounds from conversations and leverage this information for personalized assistance is crucial. However, the scarcity of high-quality data remains a fundamental challenge to evaluating and improving this capability. Traditional dataset construction methods are labor-intensive, resource-demanding, and raise privacy concerns. To address these issues, we propose a novel approach for automatic synthetic data generation and introduce the **I**mplicit **P**ersonalized **Dialog**ue (**IP-Dialog**) benchmark along with a training dataset, covering 10 tasks and 12 user attribute types. Additionally, we develop a systematic evaluation framework with four metrics to assess both attribute awareness and reasoning capabilities. We further propose five causal graphs to elucidate models' reasoning pathways during implicit personalization. Extensive experiments yield insightful observations and prove the reliability of our dataset.

IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Data

The increasing autonomy of LLM agents in handling sensitive communications, accelerated by Model Context Protocol (MCP) and Agent-to-Agent (A2A) frameworks, creates urgent privacy challenges. While recent work reveals significant gaps between LLMs' privacy Q&A performance and their agent behavior, existing benchmarks remain limited to static, simplified scenarios. We present PrivacyChecker, a model-agnostic, contextual integrity based mitigation approach that effectively reduces privacy leakage from 36.08% to 7.30% on DeepSeek-R1 and from 33.06% to 8.32% on GPT-4o, all while preserving task helpfulness. We also introduce PrivacyLens-Live, transforming static benchmarks into dynamic MCP and A2A environments that reveal substantially higher privacy risks in practical. Our modular mitigation approach integrates seamlessly into agent protocols through three deployment strategies, providing practical privacy protection for the emerging agentic ecosystem. Our data and code are available at https://anonymous.4open.science/r/PrivacyChecker-232F/.

Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents

Multi-turn jailbreak attacks simulate real-world human interactions by engaging large language models (LLMs) in iterative dialogues, exposing critical safety vulnerabilities. However, existing methods often struggle to balance semantic coherence with attack effectiveness, resulting in either benign semantic drift or ineffective detection evasion. To address this challenge, we propose Reasoning-Augmented Conversation (RACE), a novel multi-turn jailbreak framework that reformulates harmful queries into benign reasoning tasks and leverages LLMs’ strong reasoning capabilities to compromise safety alignment. Specifically, we introduce an attack state machine framework to systematically model problem translation and iterative reasoning, ensuring coherent query generation across multiple turns. Building on this framework, we design gain-guided exploration, self-play, and rejection feedback modules to preserve attack semantics, enhance effectiveness, and sustain reasoning-driven attack progression. Extensive experiments on multiple LLMs demonstrate that RACE achieves state-of-the-art attack effectiveness in complex conversational scenarios, with attack success rates (ASRs) increasing by up to 96%. Notably, our approach achieves average ASR of 83.3% against leading commercial models, including Gemini 2.0 Flashing Thinking and OpenAI o1, underscoring its potency.

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models

Large Language Models are increasingly used in applications requiring objective assessment, which could be compromised by political bias. Many studies found preferences for left-leaning positions in LLMs, but downstream effects on tasks like fact-checking remain underexplored. In this study, we systematically investigate political bias through exchanging words with euphemisms or dysphemisms in German claims. We construct minimal pairs of factually equivalent claims that differ in political connotation, to assess the consistency of LLMs in classifying them as true or false. We evaluate six LLMs and find that, more than political leaning, the presence of judgmental words significantly influences truthfulness assessment. While a few models show tendencies of political bias, this is not mitigated by explicitly calling for objectivism in prompts. Warning: This paper contains content that may be offensive or upsetting.

Downloads

Next from EMNLP 2025

CESRec: Constructing Pseudo Interactions for Sequential Recommendation via Conversational Feedback

Similar lecture

Hallucination Diversity-Aware Active Learning for Text Summarization