China

Misinformation remains one of the most significant issues in the digital age. While automated fact-checking has emerged as a viable solution, most current systems are limited to evaluating factual accuracy. However, the detrimental effect of misinformation transcends simple falsehoods; it takes advantage of how individuals perceive, interpret, and emotionally react to information. This underscores the need to move beyond factuality and adopt more human-centered detection frameworks. In this survey, we explore the evolving interplay between traditional fact-checking approaches and psychological concepts such as cognitive biases, social dynamics, and emotional responses. By analyzing state-of-the-art misinformation detection systems through the lens of human psychology and behavior, we reveal critical limitations of current methods and identify opportunities for improvement. Additionally, we outline future research directions aimed at creating more robust and adaptive frameworks, such as neuro-behavioural models that integrate technological factors with the complexities of human cognition and social influence. These approaches offer promising pathways to more effectively detect and mitigate the societal harms of misinformation.

EMNLP 2025

The Psychology of Falsehood: A Human-Centric Survey of Misinformation Detection

psychology of misinformation

claim veracity

cognitive bias

fact-checking

misinformation

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*

[**Link to Conference Handbook**](https://drive.google.com/file/d/1johU5QqVVYO4RfH7QcIORr7qrVBdzdwC/view?usp=sharing)





<br>

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

The misuse of large language models (LLMs), such as academic plagiarism, has driven the development of detectors to identify LLM-generated texts. To bypass these detectors, paraphrase attacks have emerged to purposely rewrite these texts to evade detection. Despite the success, existing methods require substantial data and computational budgets to train a specialized paraphraser, and their attack efficacy greatly reduces when faced with advanced detection algorithms. To address this, we propose \textbf{Co}ntrastive \textbf{P}araphrase \textbf{A}ttack (CoPA), a training-free method that effectively deceives text detectors using off-the-shelf LLMs. The first step is to carefully craft instructions that encourage LLMs to produce more human-like texts. Nonetheless, we observe that the inherent statistical biases of LLMs can still result in some generated texts carrying certain machine-like attributes that can be captured by detectors. To overcome this, CoPA constructs an auxiliary machine-like word distribution as a contrast to the human-like distribution generated by the LLM. By subtracting the machine-like patterns from the human-like distribution during the decoding process, CoPA is able to produce sentences that are less discernible by text detectors. Our theoretical analysis suggests the superiority of the proposed attack. Extensive experiments validate the effectiveness of CoPA in fooling text detectors across various scenarios.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors

Large language models (LLMs) are able to generate grammatically well-formed text, but how do they encode their syntactic knowledge internally? While prior work has focused largely on binary grammatical contrasts, in this work, we study the representation and control of two multidimensional hierarchical grammar phenomena—verb tense and aspect—and for each, identify distinct, orthogonal directions in residual space using linear discriminant analysis. Next, we demonstrate causal control over both grammatical features through concept steering across three generation tasks. Then, we use these identified features in a case study to investigate factors influencing effective steering in multi-token generation. We find that steering strength, location, and duration are crucial parameters for reducing undesirable side effects such as topic shift and degeneration. Our findings suggest that models encode tense and aspect in structurally organized, human-like ways, but effective control of such features during generation is sensitive to multiple factors and requires manual tuning or automated optimization.

Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect

Large language models readily memorize arbitrary training instances, such as label noise, yet they perform strikingly well on reasoning tasks. In this work, we investigate how language models memorize label noise, and why such memorization in many cases does not heavily affect generalizable reasoning capabilities. Using two controllable synthetic reasoning tasks with noisy labels, four-digit addition (FDA) and two-hop relational reasoning (THR), we discover a reliance of memorization on generalizable reasoning mechanisms: models continue to compute intermediate reasoning outputs even when retrieving memorized noisy labels, and intervening reasoning adversely affects memorization. We further show that memorization operates through distributed encoding, i.e., aggregating various inputs and intermediate results, rather than building a look-up mechanism from inputs to noisy labels. Moreover, our FDA case study reveals memorization occurs via outlier heuristics, where existing neuron activation patterns are slightly shifted to fit noisy labels. Together, our findings suggest that memorization of label noise in language models builds on, rather than overrides, the underlying reasoning mechanisms, shedding lights on the intriguing phenomenon of benign memorization.

Reason to Rote: Rethinking Memorization in Reasoning

Humans can interpret geospatial information through natural language, while the geospatial cognition capabilities of Large Language Models (LLMs) remain underexplored. Prior research in this domain has been constrained by non-quantifiable metrics, limited evaluation datasets; unclear research hierarchies further compound these limitations. Therefore, we propose a scalable benchmark and conduct a comprehensive evaluation of the geospatial route cognition of LLMs. We create a large-scale evaluation dataset comprised of 36000 routes from 12 metropolises. Then, we introduce PathBuilder, a novel tool for converting natural language instructions into navigation routes, and vice versa, bridging the gap between geospatial information and natural language. Finally, we propose a new evaluation framework and metrics to rigorously assess 9 state-of-the-art (SOTA) LLMs, on the task of route reversal. The benchmark reveals that LLMs exhibit limited ability to reverse routes: most of the reverse routes neither return to the starting point nor are similar to the optimal route. Additionally, LLMs face challenges such as low robustness in route generation and high confidence for their incorrect answers.

TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route

The emergence of text-to-image synthesis (TIS) models has significantly influenced digital image creation by producing high-quality visuals from written descriptions. Yet these models are sensitive on textual prompts, posing a challenge for novice users who may not be familiar with TIS prompt writing. Existing solutions relieve this via automatic prompt expansion or generation from a user query. However, this single-turn manner suffers from limited user-centricity in terms of result interpretability and user interactivity. Thus, we propose DialPrompt, a dialogue-based TIS prompt generation model that emphasizes user experience for novice users. DialPrompt is designed to follow a multi-turn workflow, where in each round of dialogue the model guides user to express their preferences on possible optimization dimensions before generating the final TIS prompt. To achieve this, we mined 15 essential dimensions for high-quality prompts from advanced users and curated a multi-turn dataset. Through training on this dataset, DialPrompt improves user-centricity by allowing users to perceive and control the creation process of TIS prompts. Experiments indicate that DialPrompt improves significantly in user-centricity score compared with existing approaches while maintaining a competitive quality of synthesized images. In our user evaluation, DialPrompt is highly rated by 19 human reviewers (especially novices).

Taming Text-to-Image Synthesis for Novices: User-centric Prompt Generation via Multi-turn Guidance

Conversational Speech Synthesis (CSS) aims to generate speech with natural prosody by understanding the multimodal dialogue history (MDH). The latest work predicts the accurate prosody expression of the target utterance by modeling the utterance-level interaction characteristics of MDH and the target utterance. However, MDH contains fine-grained semantic and prosody knowledge at the word level. Existing methods overlook the fine-grained semantic and prosody interaction modeling. To address this gap, we propose MFCIG-CSS, a novel Multimodal Fine-grained Context Interaction Graph-based CSS system. Our approach constructs two specialized multimodal fine-grained dialogue interaction graphs: a semantic interaction graph and a prosody interaction graph. These two interaction graphs effectively encode interactions between word-level semantics, prosody, and their influence on subsequent utterances in MDH. The encoded interaction features are then leveraged to enhance synthesized speech with natural conversational prosody. Experiments on the DailyTalk dataset demonstrate that MFCIG-CSS outperforms all baseline models in terms of prosody expressiveness. Code and speech samples are available at https://github.com/coder-speech/MFCIG-CSS.

Multimodal Fine-grained Context Interaction Graph Modeling for Conversational Speech Synthesis

The rapid growth of video platforms has transformed information dissemination and led to an explosion of multimedia content. However, this widespread reach also introduces risks, as some users exploit these platforms to spread hate speech, which is often concealed through complex rhetoric, making hateful video detection a critical challenge. Existing detection methods rely heavily on unimodal analysis or simple feature fusion, struggling to capture cross-modal interactions and reason through implicit hate in sarcasm and metaphor. To address these limitations, we propose HVGuard, the first reasoning-based hateful video detection framework with multimodal large language models (MLLMs). Our approach integrates Chain-of-Thought (CoT) reasoning to enhance multimodal interaction modeling and implicit hate interpretation. Additionally, we design a Mixture-of-Experts (MoE) network for efficient multimodal fusion and final decision-making. The framework is modular and extensible, allowing flexible integration of different MLLMs and encoders. Experimental results demonstrate that HVGuard outperforms all existing advanced detection tools, achieving an improvement of 6.88\% to 13.13\% in accuracy and 9.21\% to 34.37\% in M-F1 on two public datasets covering both English and Chinese.

HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection

Most previous work on Conversational Query Rewriting employs an end-to-end rewriting paradigm. However, this approach is hindered by the issue of multiple fuzzy expressions within the query, which complicates the simultaneous identification and rewriting of multiple positions. To address this issue, we propose a novel framework ICR (Iterative Clarification and Rewriting), an iterative rewriting scheme that pivots on clarification questions. Within this framework, the model alternates between generating clarification questions and rewritten queries. The experimental results show that our ICR can continuously improve retrieval performance in the clarification-rewriting iterative process, thereby achieving state-of-the-art performance on two popular datasets.

ICR: Iterative Clarification and Rewriting for Conversational Search

Recent studies have shown that Contrastive Language-Image Pre-training (CLIP) models are threatened by targeted data poisoning and backdoor attacks due to massive training image-caption pairs crawled from the Internet. Previous defense methods correct poisoned image-caption pairs by matching a new caption for each image. However, the matching process solely relies on the global representations of images and captions, overlooking fine-grained features of visual and textual features. It may introduce incorrect image-caption pairs and detriment the CLIP pre-training. To address their limitations, we propose an Optimal Transport-based framework to reconstruct the image-caption pairs, named OTCCLIP. We involve a new optimal transport-based distance measure between fine-grained visual and textual feature sets and re-assign new captions based on the proposed optimal transport distance. Additionally, to further reduce the negative impact of mismatched pairs, we encourage the inter- and intra-modality fine-grained alignment by employing optimal transport-based objective functions. Our experiments demonstrate that OTCCLIP can successfully decrease the attack success rates of poisoning attacks to 0% in most cases. Also, compared to previous methods, OTCCLIPsignificantly improves CLIP's zero-shot and linear probing performance trained on poisoned datasets.

Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignment

Most state-of-the-art recommendation systems rely on ID-based embedding techniques, which, while effective, face significant challenges, including high training data requirements and poor generalization in cold-start scenarios. Inspired by the success of foundation models in visual and language tasks, this work introduces a foundation model for sequential recommendation systems aimed at enhancing generalization. Our proposed RecGPT model features a novel vector quantization-based item tokenizer that creates generalized token representations, effectively capturing diverse semantic features for context-aware recommendations. Additionally, we utilize a decoder-only transformer architecture with an autoregressive modeling paradigm that incorporates bidirectional attention, allowing the model to understand item token relationships and complex user behaviors across diverse scenarios. We evaluate our model across several public datasets, targeting zero-shot and cold-start scenarios, and find significant improvements in generalization over existing methods.

Downloads

Next from EMNLP 2025

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES