China

Large language models (LLMs) have increasingly been explored as powerful text embedders. Existing LLM-based text embedding approaches often leverage the embedding of the final token, typically a reserved special token such as `[EOS]`. However, these tokens have not been intentionally trained to capture the semantics of the whole context, limiting their capacity as text embeddings, especially for retrieval and re-ranking tasks. We propose to add a new training stage before contrastive learning to enrich the semantics of the final token embedding. This stage employs bidirectional generative reconstruction tasks, namely Query2Doc (Q2D) and Doc2Query (D2Q), which interleave to anchor the `[EOS]` embedding and reconstruct either side of Query-Doc pairs. Experimental results demonstrate that our additional training stage significantly improves LLM performance on the Massive Text Embedding Benchmark (MTEB), achieving new state-of-the-art results across different LLM base models and scales.

EMNLP 2025

Training LLMs to be Better Text Embedders through Bidirectional Reconstruction

large language models (llms)

text embeddings

information retrieval

## 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*





<br>

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

poster

Recent years have witnessed remarkable advances in Large Language Models (LLMs). However, in the task of social relation recognition, Large Language Models (LLMs) encounter significant challenges due to their reliance on sequential training data, which inherently restricts their capacity to effectively model complex graph-structured relationships. To address this limitation, we propose a novel low-coupling method synergizing multimodal temporal Knowledge Graphs and Large Language Models (mtKG-LLM) for social relation reasoning. Specifically, we extract multimodal information from the videos and model the social networks as spatial Knowledge Graphs (KGs) for each scene. Temporal KGs are constructed based on spatial KGs and updated along the timeline for long-term reasoning. Subsequently, we retrieve multi-scale information from the graph-structured knowledge for LLMs to recognize the underlying social relation. Extensive experiments demonstrate that our method has achieved state-of-the-art performance in social relation recognition. Furthermore, our framework exhibits effectiveness in bridging the gap between KGs and LLMs. Our code will be released after acceptance.

Synergizing Multimodal Temporal Knowledge Graphs and Large Language Models for Social Relation Recognition

Contrastive Vision-Language Pre-training (CLIP) has recently demonstrated remarkable success in aligning vision and language. Aligning time series with text leverages the rich semantic cues of language to enhance interpretability and generalization, addressing a largely underexplored area of research. Although applying the CLIP training paradigm to time-series and language pairs is promising, it may result in label collapse due to the sparse semantic annotations and the absence of visual cues in time-series data. To address this, we introduce Time Series CLIP (TS-CLIP), a novel approach that tackles label collapse using a synonym bank mechanism. Synonym bank exploits word analogy phenomena to generate potential synonym embeddings as alignment targets. Specifically, the synonym bank facilitates aligning time series with a word distribution instead of a precise textual description. We conducted extensive zero-shot and few-shot experiments on 128 sub-datasets from the UCR archive. The results show that TS-CLIP achieves state-of-the-art (SOTA) performance in zero-shot settings on 51 datasets. Comprehensive ablation studies and visualization analyzes reveal that TS-CLIP effectively aligns time series with natural language. To the best of our knowledge, this is the first foundational model to achieve general time series and natural language alignment. TS-CLIP introduces a new paradigm for the semantic understanding of time series and opens the possibility of integrating the time series modality into multimodal large models.

TS-CLIP: Time Series Understanding by CLIP

In this paper, we propose TrInk, a Transformer-based model for ink generation, enabling parallel training and better capturing global dependencies. To better facilitate the alignment between the input text and generated stroke points, we introduce scaled positional embeddings and a Gaussian memory mask in the cross-attention module. Additionally, we design both subjective and objective evaluation pipelines to comprehensively assess the legibility and style consistency of the generated handwriting. Experiments demonstrate that our Transformer-based model achieves a 35.56% reduction in character error rate (CER) and an 29.66% reduction in word error rate (WER) on the IAM-OnDB dataset compared to previous methods. We provide an online demo page with handwriting samples from TrInk and baseline models at: https://akahello-a11y.github.io/trink-demo/

TrInk: Ink Generation with Transformer Network

For Relation Extraction (RE), the manual annotation of training data may be prohibitively expensive, since the sentences that contain the target relations in texts can be very scarce and difficult to find. It is therefore beneficial to develop an efficient method that can automatically extract training instances from unlabeled texts for training RE models. Recently, large language models (LLMs) have been adopted in various natural language processing tasks, with RE also benefiting from their advances. However, when leveraging LLMs for RE with predefined relation categories, two key challenges arise. First, in a multi-class classification setting, LLMs often struggle to comprehensively capture the semantics of every relation, leading to suboptimal results. Second, although employing binary classification for each relation individually can mitigate this issue, it introduces significant computational overhead, resulting in impractical time complexity for real-world applications. Therefore, this paper proposes a framework called M-BRe to extract training instances from unlabeled texts for RE. It utilizes three modules to combine the advantages of both of the above classification approaches: Relation Grouping, Relation Extraction, and Label Decision. Extensive experiments confirm its superior capability in discovering high-quality training samples from unlabeled texts for RE.

M-BRe: Discovering Training Samples for Relation Extraction from Unlabeled Texts with Large Language Models

Text-based person search (TBPS) enables the retrieval of person images from large-scale databases using natural language descriptions, offering critical value in surveillance applications. However, a major challenge lies in the labor-intensive process of obtaining high-quality textual annotations, which limits scalability and practical deployment. To address this, we introduce two complementary modules: Multi-Turn Text Generation (MTG) and Multi-Turn Text Interaction (MTI). MTG generates rich pseudo-labels through simulated dialogues with multimodal large language models (MLLMs), producing fine-grained and diverse visual descriptions without manual supervision. MTI refines user queries at inference time through dynamic, dialogue-based reasoning, enabling the system to interpret and resolve vague, incomplete, or ambiguous descriptions—characteristics often seen in real-world search scenarios. Together, MTG and MTI form a unified and annotation-free framework that significantly improves retrieval accuracy, robustness, and usability. Extensive evaluations demonstrate that our method achieves competitive or superior results while eliminating the need for manual captions, paving the way for scalable and practical deployment of TBPS systems.

Chat-Driven Text Generation and Interaction for Person Retrieval

Contrastive Language-Image Pre-training (CLIP) has become a cornerstone in multimodal intelligence. However, recent studies discovered that CLIP can only encode one aspect of the feature space, leading to substantial information loss and indistinctive features. To mitigate this issue, this paper introduces a novel strategy that fine-tunes a series of complementary CLIP models and transforms them into a CLIP-MoE. Specifically, we propose a model-agnostic Diversified Multiplet Upcycling (DMU) framework for CLIP. Instead of training multiple CLIP models from scratch, DMU leverages a pre-trained CLIP and fine-tunes it into a diverse set with highly cost-effective multistage contrastive learning, thus capturing distinct feature subspaces efficiently. To fully exploit these fine-tuned models while minimizing computational overhead, we transform them into a CLIP-MoE, which dynamically activates a subset of CLIP experts, achieving an effective balance between model capacity and computational cost. Comprehensive experiments demonstrate the superior performance of CLIP-MoE across various zero-shot retrieval, zero-shot image classification tasks, and downstream Multimodal Large Language Model (MLLM) benchmarks when used as a vision encoder.

CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling

Large Language Models (LLMs) rely heavily on large-scale reasoning data, but as such data becomes increasingly scarce, model self-improvement offers a promising alternative. However, this process can lead to model collapse, as the model’s output becomes overly deterministic with reduced diversity. In this work, we identify a new risk beyond model collapse, which we term the Superficial Self-Improved Reasoners phenomenon. This phenomenon indicates that while self-improvement enhances in-domain (ID) reasoning accuracy, it degrades the model’s generalized reasoning capability on out-of-domain (OOD) datasets, as the model tends to memorize the training data. Our analyses of layer importance and parameter changes reveal that reasoning-critical layers receive fewer updates compared to less relevant layers during self-improvement. To address this, we propose Iterative Model Merging (IMM), which balances reasoning improvements and generalization by merging the weights of the original and self-improved models. IMM effectively mitigates model collapse and improves generalized reasoning capability.

Superficial Self-Improved Reasoners Benefit from Model Merging

The rapid growth of text-to-video (T2V) diffusion models has raised concerns about privacy, copyright, and safety due to their potential misuse in generating harmful or misleading content. These models are often trained on numerous datasets, including unauthorized personal identities, artistic creations, and harmful materials, which can lead to uncontrolled production and distribution of such content. To address this, we propose VideoEraser, a training-free framework that prevents T2V diffusion models from generating videos with undesirable concepts, even when explicitly prompted with those concepts. Designed as a plug-and-play module, VideoEraser can seamlessly integrate with representative T2V diffusion models via a two-stage process: Selective Prompt Embedding Adjustment (SPEA) and Adversarial-Resilient Noise Guidance (ARNG). We conduct extensive evaluations across four tasks, including object erasure, artistic style erasure, celebrity erasure, and explicit content erasure. Experimental results show that VideoEraser consistently outperforms prior methods regarding efficacy, integrity, fidelity, robustness, and generalizability. Notably, VideoEraser achieves state-of-the-art performance in suppressing undesirable content during T2V generation, reducing it by 46% on average across four tasks compared to baselines.

VideoEraser: Concept Erasure in Text-to-Video Diffusion Models

Visual Question Generation (VQG) research focuses predominantly on natural images while neglecting the diagram, which is a critical component in educational materials. To meet the needs of pedagogical assessment, we propose the Diagram-Driven Course Questions Generation (DDCQG) task and construct DiagramQG, a comprehensive dataset with 15,720 diagrams and 25,798 questions across 37 subjects and 371 courses. Our approach employs \textit{course} and \textit{input} text constraints to generate course-relevant questions about specific diagram elements. We reveal three challenges of DDCQG: domain-specific knowledge requirements across courses, long-tail distribution in course coverage, and high information density in diagrams. To address these, we propose the Hierarchical Knowledge Integration framework (HKI-DDCQG), which utilizes trainable CLIP for identifying relevant diagram patches, leverages frozen vision-language models for knowledge extraction, and generates questions with trainable T5. Experiments demonstrate that HKI-DDCQG outperforms existing models on DiagramQG while maintaining strong generalizability across natural image datasets, establishing a strong baseline for DDCQG.

Diagram-Driven Course Questions Generation

Grounded Multimodal Named Entity Recognition (GMNER), which aims to extract textual entities, their types, and corresponding visual regions from image-text data, has become a critical task in multimodal information extraction. However, existing methods face two major challenges. First, they fail to address the semantic ambiguity caused by polysemy and the long-tail distribution of datasets. Second, unlike visual grounding which provides descriptive phrases, entity grounding only offers brief entity names which carry less semantic information. Current methods lack sufficient semantic interaction between text and image, hindering accurate entity-visual region matching. To tackle these issues, we propose MAKAR, a Multi-Agent framework based Knowledge-Augmented Reasoning, comprising three agents: Knowledge Enhancement, Entity Correction, and Entity Reasoning Grounding. Specifically, in the named entity recognition phase, the Knowledge Enhancement Agent leverages a Multimodal Large Language Model (MLLM) as an implicit knowledge base to enhance ambiguous image-text content with its internal knowledge. For samples with low-confidence entity boundaries and types, the Entity Correction Agent uses web search tools to retrieve and summarize relevant web content, thereby correcting entities using both internal and external knowledge. In the entity grounding phase, the Entity Reasoning Grounding Agent utilizes multi-step Chain-of-Thought reasoning to perform grounding for each entity. Extensive experiments demonstrate that our MAKAR framework achieves state-of-the-art performance on two widely used benchmark datasets. The code will be publicly released.

Downloads

Next from EMNLP 2025

Synergizing Multimodal Temporal Knowledge Graphs and Large Language Models for Social Relation Recognition

Similar lecture

Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES