China

Scaling data and model size has driven recent advances in language modeling, but this strategy falters under scenarios with strict data constraints, as in the BabyLM Challenge. However, insights from Chinchilla highlights that smaller models trained on more data outperform larger counterparts trained inadequately, emphasizing the need for compact architectures. Furthermore, while embedding weight tying is a common parameter-saving technique, we find it significantly diminishes linguistic competence in compact models. In response, we explore alternative architectural strategies that preserve the parameter efficiency of tied models without sacrificing the representational benefits of untied embeddings. Consequently, we introduce SLlama a Llama3 architecture variant which incorporates targeted modifications - Repeated Reduced Hidden Size and Projection (RRHP), Permutated Weight Attention (PWA), Shared Projection Multi-Layer Perceptron (SPMLP), and Layer Weight Sharing - to compress transformer components. Without relying on distillation, SLlama achieves a 31.72% improvement in linguistic knowledge acquisition over the BabyLlama baseline, with a comparable GLUE score and significantly lower parameter count. These results demonstrate that well-designed, compact models can rival larger ones under strict data constraints.

EMNLP 2025

SLlama: Parameter-Efficient Language Model Architecture for Enhanced Linguistic Competence Under Strict Data Constraints

strict data constraint

low-resource methods for nlp

compact models

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.

Recent advances in large language models (LLMs) have enabled strong reasoning capabilities through Chain-of-Thought (CoT) prompting, which elicits step-by-step problem solving, but often at the cost of excessive verbosity in intermediate outputs, leading to increased computational overhead. We propose Sketch-of-Thought (SoT), a prompting framework that integrates cognitively inspired reasoning paradigms with linguistic constraints to reduce token usage while preserving reasoning accuracy. SoT is designed as a flexible, modular approach and is instantiated with three paradigms—Conceptual Chaining, Chunked Symbolism, and Expert Lexicons—each tailored to distinct reasoning tasks and selected dynamically at test-time by a lightweight routing model. Across 15 reasoning datasets spanning multiple domains, languages, and modalities, SoT achieves token reductions of up to 78% with minimal accuracy loss. In tasks such as mathematical and multi-hop reasoning, it even improves accuracy while shortening outputs.

Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching

LLM inference for enterprise applications, such as summarization, RAG, and code-generation, typically observe much longer prompt than generations, leading to high prefill cost and response latency. We present SwiftKV, a novel model transformation and distillation procedure targeted at reducing the prefill compute (in FLOPs) of prompt tokens while preserving high generation quality. First, SwiftKV prefills later layers' KV cache using an earlier layer's output, allowing prompt tokens to skip those later layers. Second, SwiftKV employs a lightweight knowledge-preserving distillation procedure that can adapt existing LLMs with minimal accuracy impact. Third, SwiftKV can naturally incorporate KV cache compression to improve inference performance in low-memory scenarios. Our comprehensive experiments show that SwiftKV can effectively reduce prefill computation by 25-50% across several LLM families while incurring minimum quality degradation. In the end-to-end inference serving, SwiftKV realizes up to 2x higher aggregate throughput and 60% lower time per output token. It can achieve a staggering 560 TFlops/GPU of normalized inference throughput, which translates to 16K tokens/s for Llama-3.1-70B. SwiftKV is open-sourced at https://anonymized.link.

SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation

Natural Language Inference (NLI) is a fundamental task in Natural Language Processing (NLP), yet adapting NLI models to new domains remains challenging due to the high cost of collecting domain-specific training data. While prior work proposed 15 sentence transformation rules to automate training data generation, these rules insufficiently capture the diversity of natural language. We propose a novel framework that combines Out-of-Distribution (OOD) detection and BERT-based clustering to identify premise-hypothesis pairs in the SNLI dataset that are not covered by existing rules and to discover four new transformation rules from them. Using these rules with Chain-of-Thought (CoT) prompting and Large Language Models (LLMs), we generate high-quality training data and augment the SNLI dataset. Our method yields consistent performance improvements across dataset sizes, achieving +0.85%p accuracy on 2k and +0.15%p on 550k samples. Furthermore, a distribution-aware augmentation strategy enhances performance across all scales.

Rule Discovery for Natural Language Inference Data Generation Using Out-of-Distribution Detection

Fine-tuning large language models (LLMs) faces significant memory challenges due to the high cost of back-propagation. MeZO addresses this using zeroth-order (ZO) optimization, matching memory usage to inference but suffering from slow convergence due to varying curvatures across model parameters. To overcome this limitation, We propose HELENE, a scalable and memory-efficient optimizer that integrates annealed A-GNB gradients with diagonal Hessian estimation and layer-wise clipping as a second-order pre-conditioner. HELENE provably accelerates and stabilizes convergence by reducing dependence on total parameter space and scaling with the largest layer dimension. Experiments on RoBERTa-large and OPT-1.3B show up to a 20× speedup over MeZO with an average accuracy improvement of 1.5%. HELENE supports full and parameter-efficient fine-tuning, outperforming several state-of-the-art optimizers.

HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization

Recent studies have demonstrated that many layers are functionally redundant in large language models (LLMs), enabling model compression by removing these layers to reduce inference cost. While such approaches can improve efficiency, indiscriminate layer pruning often results in significant performance degradation. In this paper, we propose **GRASP** (**G**radient-based **R**etention of **A**daptive **S**ingular **P**arameters), a novel compression framework that mitigates this issue by preserving sensitivity-aware singular values. Unlike direct layer pruning, GRASP leverages gradient-based attribution on a small calibration dataset to adaptively identify and retain critical singular components. By replacing redundant layers with only a minimal set of parameters, GRASP achieves efficient compression while maintaining strong performance with minimal overhead. Experiments across multiple LLMs show that GRASP consistently outperforms existing compression methods, achieving 90% of the original model's performance under a 20% compression ratio.

GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression

Vision-Language-Action (VLA) models have made substantial progress by leveraging the robust capabilities of Visual Language Models (VLMs). However, VLMs' significant parameter size and autoregressive (AR) decoding nature impose considerable computational demands on VLA models. While Speculative Decoding (SD) has shown efficacy in accelerating Large Language Models (LLMs) by incorporating efficient drafting and parallel verification, allowing multiple tokens to be generated in one forward pass, its application to VLA models remains unexplored. This work introduces Spec-VLA, an SD framework designed to accelerate VLA models. Due to the difficulty of the action prediction task and the greedy decoding mechanism of the VLA models, the direct application of the advanced SD framework to the VLA prediction task yields a minor speed improvement. To boost the generation speed, we propose an effective mechanism to relax acceptance utilizing the relative distances represented by the action tokens of the VLA model. Empirical results across diverse test scenarios affirm the effectiveness of the Spec-VLA framework, and further analysis substantiates the impact of our proposed strategies, which enhance the acceptance length by 44\%, achieving 1.42times speedup compared with the OpenVLA baseline, without compromising the success rate. The success of the Spec-VLA framework highlights the potential for broader application of speculative execution in VLA prediction scenarios.

Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance

Multilabel text classification is an essential task in NLP applications. Traditional methods require extensive labeled data and are limited to fixed label sets. Extracting labels by LLMs is more effective and universal, but incurs high computational costs. In this work, we introduce a distillation-based T5 generalist model for zero-shot MLTC and few-shot fine-tuning. Our model accommodates variable label sets with general domain-agnostic pertaining, while modeling dependency between labels. Experiments show that our approach outperforms baselines of similar size on three few-shot tasks. Our code is available at https://anonymous.4open.science/r/t5-multilabel-0C32/README.md

Leveraging Text-to-Text Transformers as Classifier Chain for Few-Shot Multi-Label Classification

Tokenization is a fundamental step in natural language processing (NLP) and other sequence modeling domains, where the choice of vocabulary size significantly impacts model performance. Despite its importance, selecting an optimal vocabulary size remains underexplored, typically relying on heuristics or dataset-specific choices. In this work, we propose a principled method for determining the vocabulary size by analyzing token frequency distributions through Zipf’s law. We show that downstream task performance correlates with how closely token distributions follow power-law behavior, and that aligning with Zipfian scaling improves both model efficiency and effectiveness. Extensive experiments across NLP, genomics, and chemistry demonstrate that models consistently achieve peak performance when the token distribution closely adheres to Zipf’s law, establishing Zipfian alignment as a robust and generalizable criterion for vocabulary size selection.

Pre-trained Models Perform the Best When Token Distributions Follow Zipf’s Law

English, as a very high-resource language, enables the pretraining of high-quality large language models (LLMs). However, the same cannot be said for most other languages, likely due to a gap in the quality and diversity of available multilingual pretraining corpora. In this work, we find that machine-translated texts from a high-quality English source can contribute significantly to the pretraining quality of multilingual LLMs. Concretely, we translate FineWeb-Edu, a high-quality English web dataset, into nine languages. resulting in a 1.7-trillion-token dataset, which we call TransWebEdu and pretrain a 1.3B-parameter model, TransWebLLM, from scratch on this dataset. Across Non-English reasoning tasks, we show that TransWebLLM matches or even outperforms multilingual LLMs of similar size, including Llama3.2, Qwen2.5, and Gemma3, despite being trained on an order of magnitude less data. Moreover, we show that adding less than 5% of TransWebEdu as domain-specific pretraining data sets new state-of-the-art results in Arabic, Indonesian, Swahili, and Welsh for understanding and commonsense reasoning tasks. To promote reproducibility, we release our corpus, models, and training pipeline under Open Source Initiative-approved licenses.

Multilingual Language Model Pretraining using Machine-translated Data

Parallel Data Curation (PDC) techniques aim to filter out noisy parallel sentences from web-mined corpora. Ranking sentence pairs using similarity scores on sentence embeddings derived from Pre-trained Multilingual Language Models (multiPLMs) is the most common PDC technique. However, previous research has shown that the choice of the multiPLM significantly impacts the quality of the filtered parallel corpus, and the NMT models trained using such data show a disparity across multiPLMs. This paper shows that this disparity is due to different multiPLMs being biased towards certain types of sentence pairs, which are treated as noise from an NMT point of view. We show that such noisy parallel sentences can be removed to a certain extent by employing a series of heuristics. The curated corpus leads to producing better results by NMT models while minimizing the disparity across multiPLMs. We publicly release the source code and the curated datasets.

Downloads

Next from EMNLP 2025

Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching