China

Retrieval-augmented generation (RAG) enhances large language models by incorporating context retrieved from external knowledge sources. While the effectiveness of the retrieval module is typically evaluated with relevance-based ranking metrics, such metrics may be insufficient to reflect the retrieval&#39;s impact on the final RAG result, especially in long-form generation scenarios. We argue that providing a comprehensive retrieval-augmented context is important for long-form RAG tasks like report generation and propose metrics for assessing the context independent of generation. We introduce CRUX, a \textbf{C}ontrolled \textbf{R}etrieval-a\textbf{U}gmented conte\textbf{X}t evaluation framework designed to directly assess retrieval-augmented contexts. This framework uses human-written summaries to control the information scope of knowledge, enabling us to measure how well the context covers information essential for long-form generation. CRUX uses question-based evaluation to assess RAG&#39;s retrieval in a fine-grained manner. Empirical results show that CRUX offers more reflective and diagnostic evaluation. Our findings also reveal substantial room for improvement in current retrieval methods, pointing to promising directions for advancing RAG&#39;s retrieval. Our data and code are publicly available to support and advance future research on retrieval.\footnote{https://anonymous.4open.science/r/rag-rerank-85CF }

EMNLP 2025

Controlled Retrieval-augmented Context Evaluation for Long-form RAG

Retrieval-augmented generation (RAG) enhances large language models by incorporating context retrieved from external knowledge sources. While the effectiveness of the retrieval module is typically evaluated with relevance-based ranking metrics, such metrics may be insufficient to reflect the retrieval's impact on the final RAG result, especially in long-form generation scenarios. We argue that providing a comprehensive retrieval-augmented context is important for long-form RAG tasks like report generation and propose metrics for assessing the context independent of generation. We introduce CRUX, a \textbf{C}ontrolled \textbf{R}etrieval-a\textbf{U}gmented conte\textbf{X}t evaluation framework designed to directly assess retrieval-augmented contexts. This framework uses human-written summaries to control the information scope of knowledge, enabling us to measure how well the context covers information essential for long-form generation. CRUX uses question-based evaluation to assess RAG's retrieval in a fine-grained manner. Empirical results show that CRUX offers more reflective and diagnostic evaluation. Our findings also reveal substantial room for improvement in current retrieval methods, pointing to promising directions for advancing RAG's retrieval. Our data and code are publicly available to support and advance future research on retrieval.\footnote{https://anonymous.4open.science/r/rag-rerank-85CF }

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.

Mixture-of-Experts (MoE) models are crucial for scaling model capacity while controlling inference costs. While integrating MoE into multimodal models like CLIP improves performance, training these models is notoriously challenging and expensive. We propose CLIP-Upcycling (CLIP-UP), an efficient alternative training strategy that converts a pre-trained dense CLIP model into a sparse MoE architecture. Through extensive experimentation with various settings and auxiliary losses, we demonstrate that CLIP-UP significantly reduces training complexity and cost. Remarkably, our sparse CLIP B/16 model, trained with CLIP-UP, outperforms its dense counterpart by 7.2% and 6.6% on COCO and Flickr30k text-to-image Recall@1 benchmarks respectively. It even surpasses the larger CLIP L/14 model on this task while using only 30% of the inference FLOPs. We further demonstrate the generalizability of our training recipe across different scales, establishing sparse upcycling as a practical and scalable approach for building efficient, high-performance CLIP models.

CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling

Small Language Models (SLMs) offer computational efficiency and accessibility, yet a systematic evaluation of their performance and environmental impact remains lacking. We introduce SLM-Bench, the first benchmark specifically designed to assess SLMs across multiple dimensions, including accuracy, computational efficiency, and sustainability metrics. SLM-Bench evaluates 15 SLMs on 9 NLP tasks using 23 datasets spanning 14 domains. The evaluation is conducted on 4 hardware configurations, providing a rigorous comparison of their effectiveness. Unlike prior benchmarks, SLM-Bench quantifies 11 metrics across correctness, computation, and consumption, enabling a holistic assessment of efficiency trade-offs. Our evaluation considers controlled hardware conditions, ensuring fair comparisons across models. We develop an open-source benchmarking pipeline with standardized evaluation protocols to facilitate reproducibility and further research. Our findings highlight the diverse trade-offs among SLMs, where some models excel in accuracy while others achieve superior energy efficiency. SLM-Bench sets a new standard for SLM evaluation, bridging the gap between resource efficiency and real-world applicability.

SLM-Bench: A Comprehensive Benchmark of Small Language Models on Environmental Impacts

Maltese is a unique Semitic language that has evolved under extensive influence from Romance and Germanic languages, particularly Italian and English. Despite its Semitic roots, its orthography is based on the Latin script, creating a gap between it and its closest linguistic relatives in Arabic. In this paper, we explore whether Arabic-language resources can support Maltese natural language processing (NLP) through cross-lingual augmentation techniques. We investigate multiple strategies for aligning Arabic textual data with Maltese, including various transliteration schemes and machine translation (MT) approaches. As part of this, we also introduce novel transliteration systems that better represent Maltese orthography. We evaluate the impact of these augmentations on monolingual and mutlilingual models and demonstrate that Arabic-based augmentation can significantly benefit Maltese NLP tasks.

Data Augmentation for Maltese NLP using Transliterated and Machine Translated Arabic Data

Scientific discovery catalyzes human intellectual advances, driven by the cycle of hypothesis generation, experimental design, evaluation, and assumption refinement. Central to this process is causal inference, uncovering the mechanisms behind observed phenomena. While randomized experiments provide strong inferences, they are often infeasible due to ethical or practical constraints. However, observational studies are prone to confounding or mediating biases. While crucial, identifying such backdoor paths is expensive and heavily depends on scientists' domain knowledge to generate hypotheses. We introduce a novel benchmark where the objective is to complete a partial causal graph. We design a benchmark with varying difficulty levels with over 4000 queries. We show the strong ability of LLMs to hypothesize the backdoor variables between a cause and its effect. Unlike simple knowledge memorization of fixed associations, our task requires the LLM to reason according to the context of the entire graph

Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables

Natural Language Processing (NLP) has catalyzed a paradigm shift in Computer-Aided Synthesis Planning (CASP), reframing chemical synthesis prediction as a sequence-to-sequence modeling problem over molecular string representations like SMILES. This framing has enabled the direct application of language models to chemistry, yielding impressive benchmark scores on the USPTO dataset, a large text corpus of reactions extracted from US patents. However, we show that USPTO’s patent-derived data are both industrially biased and incomplete: they omit many fundamental transformations essential for practical real-world synthesis. Consequently, models trained exclusively on USPTO perform poorly on simple, pharmaceutically relevant reactions despite high benchmark scores. Our findings highlight a broader concern in applying standard NLP pipelines to scientific domains without rethinking data and evaluation: models may learn dataset artifacts rather than domain reasoning. We argue for the development of chemically meaningful benchmarks, greater data diversity, and interdisciplinary dialogue between the NLP community and domain experts to ensure real-world applicability.

Rethinking NLP for Chemistry: A Critical Look at the USPTO Benchmark

Although synthetic data has changed various aspects of information retrieval (IR) pipelines, the main training paradigm remains: contrastive learning with binary relevance labels, where one positive document is compared against several negatives using the InfoNCE loss. This objective treats all documents that are not explicitly annotated as relevant on an equally negative footing, regardless of their actual degree of relevance, thus missing subtle nuances useful for ranking. To overcome this limitation, in this work, we forgo real documents and annotations and use large language models to directly generate synthetic documents that answer the MS MARCO queries according to _several different levels of relevance_. We also propose using Wasserstein distance as a more effective loss function for training transformer-based retrievers with graduated relevance labels. Our experiments on MS MARCO and BEIR benchmark show that our proposed approach outperforms conventional training with InfoNCE by a large margin. Without using any real documents, our method significantly improves self-supervised retrievers and is more robust to distribution shift compared to contrastive learning using real data. Our method also successfully integrates existing real data into the synthetic ranking context, further boosting the performance. Overall, we show that generating multi-level ranking contexts is a better approach to synthetic data generation for IR than just generating the standard positive and negative documents.

Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance

This work introduces SteerVLM, a lightweight steering module designed to guide Vision-Language Models (VLMs) towards outputs that better adhere to desired instructions. Our approach learns from the latent embeddings of paired prompts encoding target and converse behaviors to dynamically adjust activations connecting the language modality with image context. This allows for fine-grained, inference-time control over complex output semantics without modifying model weights while preserving performance on off-target tasks. Our steering module requires learning parameters equal to 0.14% of the original VLM's size. Our steering module gains model control through dimension-wise activation modulation and adaptive steering across layers without requiring pre-extracted static vectors or manual tuning of intervention points. Furthermore, we introduce VNIA (Visual Narrative Intent Alignment), a multimodal dataset specifically created to facilitate the development and evaluation of VLM steering techniques. Our method outperforms existing intervention techniques on steering and hallucination mitigation benchmarks for VLMs and proposes a robust solution for multimodal model control through activation engineering.

SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models

Dense retrieval models usually adopt vectors from the last hidden layer of the document encoder to represent a document, which is in contrast to the fact that representations in different layers of a pre-trained language model usually contain different kinds of linguistic knowledge, and behave differently during fine-tuning. Therefore, we propose to investigate utilizing representations from multiple encoder layers to make up the representation of a document, which we denote Multi-layer Representations (MLR). We first investigate how representations in different layers affect MLR's performance under the multi-vector retrieval setting, and then propose to leverage pooling strategies to reduce multi-vector models to single-vector ones to improve retrieval efficiency. Experiments demonstrate the effectiveness of MLR over dual encoder, ME-BERT and ColBERT in the single-vector retrieval setting, as well as demonstrate that it works well with other advanced training techniques such as retrieval-oriented pre-training and hard negative mining.

Investigating Multi-layer Representations for Dense Passage Retrieval

We introduce DIPLomA (Decoupled Instruction-Preserving Language Adaptation), a lightweight and scalable method for adapting instruction-tuned large language models (LLMs) to low-resource languages without requiring expensive large-scale post-training. Our approach decouples language adaptation from post-training alignment by first continually pretraining a foundational LLM on monolingual target-language data, then injecting instruction-following capabilities via delta-based weight merging from the instructed counterpart of the base LLM—drawing inspiration from adapter-based transfer. We evaluate DIPLomA on Basque and validate its generality on Welsh and Swahili, demonstrating consistent and substantial gains in instruction-following, linguistic proficiency, and safety. Compared to strong baselines, our method achieves average relative improvements of 50 points in Basque, 63 in Welsh, and 51 in Swahili, while preserving the original model’s multilingual performance. These results highlight DIPLomA as an effective, resource-efficient strategy for bringing high-quality instruction alignment to underrepresented languages at scale.

DIPLomA: Efficient Adaptation of Instructed LLMs to Low-Resource Languages via Post-Training Delta Merging

In this work, we conduct an in-depth analysis of code retrieval by systematically masking specific features while preserving code functionality. Our discoveries include: (1) although trained on code, current retrievers heavily rely on surface-level textual features (e.g., docstrings, identifier names), and (2) they exhibit a strong bias towards well-documented code, even if the documentation is irrelevant. Based on our discoveries, we propose SACL, a framework that enriches textual information and reduces bias by augmenting code or structural knowledge with semantic information. Extensive experiments show that SACL substantially improves code retrieval (e.g., by 12.8% / 9.4% / 7.0% Recall@1 on HumanEval / MBPP / SWE-Bench-Lite), which also leads to better code generation performance (e.g., by 4.88% Pass@1 on HumanEval).

Downloads

Next from EMNLP 2025

CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES