China

Query generation is a critical task for web search engines (e.g. Google, Bing) and recommendation systems. Recently, state-of-the-art query generation methods leverage Large Language Models (LLMs) for their strong capabilities in context understanding and text generation. However, they still face challenges in generating high-quality queries in terms of inferring user intent based on their web search interaction history. In this paper, we propose Token-level Proximal Policy Optimization (TPPO), a noval approach designed to empower LLMs perform better in query generation through fine-tuning. TPPO is based on the Reinforcement Learning from AI Feedback (RLAIF) paradigm, consisting of a token-level reward model and a token-level proximal policy optimization module to address the sparse reward challenge in traditional RLAIF frameworks. We conducted experiments on both open-source dataset and an industrial dataset that was collected from a globally-used search engine, demonstrating that TPPO significantly improves the performance of query generation for LLMs and outperforms its existing competitors.

EMNLP 2025

Token-level Proximal Policy Optimization for Query Generation

application

distillation

data augmentation

## 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.

technical paper

While Vision Language Models (VLMs) are trained to learn conceptual representations (generalized knowledge across many instances), they are typically used to analyze individual instances. When evaluation instances are atypical, this paradigm results in tension between two priors in the model. The first is a pragmatic prior that the textual and visual input are both relevant, arising from VLM finetuning on congruent inputs; the second is a semantic prior that the conceptual representation is generally true for instances of the category. In order to understand how VLMs trade-off these priors, we introduce a new evaluation dataset, VISaGE, consisting of both typical and exceptional images. In carefully balanced experiments, we show that VLMs are typically dominated by the semantic prior, which arises from the language modality, when answering queries about instances. In contrast, conceptual understanding degrades when the assumption of congruency underlying the pragmatic prior is violated with incongruent images.

VISaGE: Understanding Visual Generics and Exceptions

Although transformers are widely used for various code-specific tasks, they have some significant limitations. In this paper, we investigate State Space Models (SSMs) as a potential alternative to transformers for code understanding tasks, such as code retrieval, classification, and clone detection. Previous research has already demonstrated that SSMs are more compute-efficient than transformers. In our work, we show that SSMs are also more sample-efficient and can effectively extrapolate to longer contexts (beyond the pretraining context) during fine-tuning. Through comprehensive experiments, we demonstrate that SSMs could serve as a viable alternative to transformers for code understanding tasks, while addressing some of the major limitations associated with transformers.

CodeSSM: Towards State Space Models for Code Understanding

Reasoning models have demonstrated remarkable performance on complex tasks by generating long reasoning traces prior to producing final answers. However, previous research on long-context scaling in language models has generally focused on managing lengthy input prompts instead of producing long outputs. To leverage the strong long context understanding abilities of current models, we introduce Understanding-to-Reasoning Transition (URT) fine-tuning, a sequence-level curriculum learning framework that gradually shifts a model’s focus from interpreting long chain-of-thoughts to generating them. By incorporating partial reasoning steps in the input context, URT naturally exposes the model to diverse prompt lengths during training, preserving its performance on long-context comprehension while developing advanced reasoning capabilities. Experiments on rigorous reasoning benchmarks, including AIME24 and GPQA Diamond, reveal that our approach surpasses standard fine-tuning by over 10%, while maintaining robust performance on the understanding tasks in RULER.

Long Chain-of-Thought Fine-tuning via Understanding-to-Reasoning Transition

Standard Byte-Pair Encoding (BPE) tokeniza- tion compresses text by pairing a learned token vocabulary with a detailed merge list. Recent work has shown that this merge list exposes a potential attack surface for extracting informa- tion about language model’s training data. In this paper, we explore the downstream impact of BPE inference algorithms that do not rely on this merge list at all, and hence differ from the encoding process during the BPE training. To address this question, we investigate two broad classes of BPE inference schemes that differ from BPE appliction during training: a) targetted deviation from merge-lists including random merge orders, and various corruptions of merge list involving deletion/truncation, and b) non-targetted BPE inference algorithms that do not depend on the merge list but focus on compressing the text either greedily or exactly. Extensive experiments across diverse language modeling tasks like accuracy-based QA bench- marks, machine translation, and open-ended generation reveal that while the targetted devi- ation from the merge lists exhibit significant degradation in language model performance, the non-targetted merge-list free inference algo- rithms result in minimal impact on downstream performance that is often much smaller than expected. These findings pave way for simpler and potentially more privacy-preserving tok- enization schemes that do not catastrophically compromise model performance.

Train It and Forget It: Merge Lists are Unnecessary for BPE Inference in Language Models

Growing literature explores toxicity and polarization in discourse, with comparatively less work on characterizing what makes dialogue prosocial and constructive. We explore conversational discourse and investigate a method for characterizing its quality built upon the notion of ``responsivity''---whether one person's conversational turn is responding to a preceding turn. We develop and evaluate methods for quantifying responsivity---first through semantic similarity of speaker turns, and second by leveraging state-of-the-art large language models (LLMs) to identify the relation between two speaker turns. We evaluate both methods against a ground truth set of human-annotated conversations. Furthermore, selecting the better performing LLM-based approach, we characterize the nature of the response---whether it responded to that preceding turn in a substantive way or not. We view these responsivity links as a fundamental aspect of dialogue but note that conversations can exhibit significantly different responsivity structures. Accordingly, we then develop conversation-level derived metrics to address various aspects of conversational discourse. We use these derived metrics to explore other conversations and show that they support meaningful characterizations and differentiations across a diverse collection of conversations.

Computational Analysis of Conversation Dynamics through Participant Responsivity

Word-level quality estimation (QE) methods aim to detect erroneous spans in machine translations, which can direct and facilitate human post-editing.
While the accuracy of word-level QE systems has been assessed extensively, their usability and downstream influence on the speed, quality and editing choices of human post-editing remain understudied. In this study, we investigate the impact of word-level QE on machine translation (MT) post-editing in a realistic setting involving 42 professional post-editors across two translation directions. We compare four error-span highlight modalities, including supervised and uncertainty-based word-level QE methods, for identifying potential errors in the outputs of a state-of-the-art neural MT model. Post-editing effort and productivity are estimated from behavioral logs, while quality improvements are assessed by word- and segment-level human annotation. We find that domain, language and editors' speed are critical factors in determining highlights' effectiveness, with modest differences between human-made and automated QE highlights underlining a gap between accuracy and usability in professional workflows.

QE4PE: Word-level Quality Estimation for Human Post-Editing

We introduce MultiBLiMP 1.0, a massively multilingual benchmark of linguistic minimal pairs, covering 101 languages and 2 types of subject-verb agreement, containing more than 128,000 minimal pairs. Our minimal pairs are created using a fully automated pipeline, leveraging the large-scale linguistic resources of Universal Dependencies and UniMorph. MultiBLiMP 1.0 evaluates abilities of LLMs at an unprecedented multilingual scale, and highlights the shortcomings of the current state-of-the-art in modelling low-resource languages.

MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs

Text-to-SQL is an important task that helps access databases by generating SQL queries. Currently, correcting the generated SQL based on large language models (LLMs) automatically is an effective method to enhance the quality of the generated SQL. However, previous research shows that it is hard for LLMs to detect mistakes in SQL directly, leading to poor performance. Therefore, in this paper, we propose to employ the decomposed correction to enhance text-to-SQL performance. We first demonstrate that detecting and fixing mistakes based on the decomposed sub-tasks is easier than using SQL directly. Then, we introduce Decomposed Automation Correction (DAC), which first generates the entities and skeleton corresponding to the question, and then compares the differences between the initial SQL and the generated entities and skeleton as feedback for correction. Experimental results show that, compared with the previous automation correction method, DAC improves performance by 1.4% of Spider, Bird, and KaggleDBQA on average, demonstrating the effectiveness of DAC.

DAC: Decomposed Automation Correction for Text-to-SQL

Multimodal Retrieval-Augmented Generation (MM-RAG) has emerged as a promising approach for enhancing the reliability and factuality of large vision-language models (LVLMs). While end-to-end loss backpropagation is infeasible due to non-differentiable operations during the forward process, current methods primarily focus on component-level optimizations, necessitate extensive component-specific training datasets and suffer from a gap between local and global optimization objectives. In this paper, we propose a new paradigm that backpropagates global rewards from the system output to each component and then transforms these rewards into specific local losses, enabling each component to perform gradient descent and thus ensuring end-to-end optimization. Specifically, we first insert two lightweight multimodal components, a query translator and an adaptive reranker, to address the heterogeneity of multimodal knowledge and the varying knowledge demands for different questions, and then tune only these inserted components using our proposed paradigm to integrate the entire system. Our method achieves SOTA performance on multiple knowledge-intensive multimodal benchmarks with high training efficiency, relying exclusively on supervised signals from an external reward model. Experimental results and our detailed analysis of the evolution of components during training collectively reveal the advantages and considerable potential of this paradigm as a promising direction for MM-RAG research.

End-to-End Optimization for Multimodal Retrieval-Augmented Generation via Reward Backpropagation

In recent years, driven by advancements in the diffusion process, Text-to-Image (T2I) models have rapidly developed. However, evaluating T2I models remains a significant challenge. While previous research has thoroughly assessed the quality of generated images and image-text alignment, there has been little study on the creativity of these models. In this work, we defined the creativity of T2I models, inspired by previous definitions of machine creativity. We also proposed corresponding metrics and designed a method to test the reliability of the metric. Additionally, we developed a fully automated pipeline capable of transforming existing image-text datasets into benchmarks tailored for evaluating creativity, specifically through text vector retrieval and the text generation capabilities of large language models (LLMs). Finally, we conducted a series of tests and analyses on the evaluation methods for T2I model creativity and the factors influencing the creativity of the models, revealing that current T2I models demonstrate a lack of creativity. The code and benchmark will be released.

Downloads

Next from EMNLP 2025

VISaGE: Understanding Visual Generics and Exceptions

Similar lecture

Skeletons Matter: Dynamic Data Augmentation for Text-to-Query