China

Prompting-based conversational query reformulation has emerged as a powerful approach for conversational search, refining ambiguous user queries into standalone search queries. Best-of-N reformulation over the generated candidates via prompting shows impressive potential scaling capability. However, both the previous tuning methods (training time) and adaptation approaches (test time) can not fully unleash their benefits. In this paper, we propose AdaRewriter, a novel framework for query reformulation using an outcome-supervised reward model via test-time adaptation. By training a lightweight reward model with contrastive ranking loss, AdaRewriter selects the most promising reformulation during inference. Notably, it can operate effectively in black-box systems, including commercial LLM APIs. Experiments on five conversational search datasets show that AdaRewriter significantly outperforms the existing methods across most settings, demonstrating the potential of test-time adaptation for conversational query reformulation.

EMNLP 2025

AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation

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.

Multi-hop question answering (QA) remains challenging, as solutions must reliably integrate and reconcile evidence from multiple sources without succumbing to error propagation. While large language models (LLMs) have achieved substantial improvements via chain-of-thought (CoT) prompting and retrieval-augmented generation, these methods typically adopt a forward-only workflow—early mistakes persist throughout inference, and contradictions discovered later cannot systematically trigger re-evaluation. To address this limitation, we present ReAgent, a reversible multi-agent reasoning framework. Specifically, ReAgent enables agents to backtrack to earlier valid states when conflicts arise, thereby isolating and rectifying flawed assumptions before they undermine subsequent reasoning. Our approach combines explicit local and global rollback protocols with modular role specialization, resulting in a flexible and error-tolerant pipeline. Empirical evaluation on three multi-hop QA benchmarks demonstrates consistent performance gains of approximately 6% over forward-only baselines, in addition to enhanced interpretability. These findings highlight the value of non-monotonic, backtracking-driven inference in complex QA scenarios and point to broader implications for multi-agent collaboration in knowledge-intensive tasks.

ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA

Multimodal event extraction task aims to identify event types and arguments from visual and textual representations related to events. Due to the high cost of multimedia training data, previous methods mainly focused on weakly alignment of excellent unimodal encoders. However, they ignore the conflict between event understanding and image recognition, resulting in redundant feature perception affecting the understanding of multimodal events. In this paper, we propose a multimodal event extraction strategy with a multi-level redundant feature selection mechanism, which enhances the event understanding ability of multimodal large language models by leveraging knowledge editing techniques, and requires no additional parameter optimization work. Extensive experiments show that our method outperforms the state-of-the-art (SOTA) baselines on the M2E2 benchmark. Compared with the highest baseline, we achieve a 34% improvement of precision on event extraction and a 11% improvement of F1 on argument extraction.

Multimedia Event Extraction with LLM Knowledge Editing

Advertising banners are critical for capturing user attention and enhancing advertising campaign effectiveness. Creating aesthetically pleasing banner designs while conveying the campaign messages is challenging due to the large search space involving multiple design elements. Additionally, advertisers need multiple sizes for different displays and various versions to target different sectors of audiences. Since design is intrinsically an iterative and subjective process, flexible editability is also in high demand for practical usage. While current models have served as assistants to human designers in various design tasks, they typically handle only segments of the creative design process or produce pixel-based outputs that limit editability. This paper introduces a training-free framework for fully automated banner ad design creation, enabling frontier multimodal large language models (MLLMs) to streamline the production of effective banners with minimal manual effort across diverse marketing contexts. We present BannerAgency, an MLLM agent system that collaborates with advertisers to understand their brand identity and banner objectives, generates matching background images, creates blueprints for foreground design elements, and renders the final creatives as editable components in Figma or SVG formats rather than static pixels. To facilitate evaluation and future research, we introduce BannerRequest400, a benchmark featuring 100 unique logos paired with 400 diverse banner requests. Through quantitative and qualitative evaluations, we demonstrate the framework's effectiveness, emphasizing the quality of the generated banner designs, their adaptability to various banner requests, and their strong editability enabled by this component-based approach.

BannerAgency: Advertising Banner Design with Multimodal LLM Agents

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.

Training LLMs to be Better Text Embedders through Bidirectional Reconstruction

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.

Downloads

Next from EMNLP 2025

ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES