China

Small language models (SLMs) are gaining attention for their lower computational and memory needs while maintaining strong performance. However, efficiently deploying SLMs on resource-constrained devices remains a significant challenge. Post-training quantization (PTQ) is a widely used compression technique that reduces memory usage and inference computation, yet existing methods face challenges in inefficient bit-width allocation and insufficient fine-grained quantization adjustments, leading to suboptimal performance, particularly at lower bit-widths. To address these challenges, we propose multi-level weight quantization (MLWQ), which facilitates the efficient deployment of SLMs. Our method enables more effective bit-width allocation by jointly considering inter-layer loss and intra-layer salience. Furthermore, we propose a fine-grained partitioning of intra-layer salience to support the tweaking of quantization parameters within each group. Experimental results show that MLWQ achieves superior performance compared to state-of-the-art methods, providing an effective approach for the efficient deployment of SLMs while maintaining model accuracy.

EMNLP 2025

MLWQ: Efficient Small Language Model Deployment via Multi-Level Weight Quantization

small language models

weight quantization

model compression

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible. The experience for on-site participants would closely approximate a normal pre-COVID *ACL conference, with 5-6 thematically organized parallel sessions and live Q/A and interactive discussion immediately after the talks. Presentations by virtual participants will be equitably interleaved with those of on-site participants, projected on the auditorium screens as if on-site, and also followed immediately by live Q/A and interactive discussion at a time during reasonable waking hours for the virtual presenter. For all participants, on-site and virtual, who are unable to attend a session due to either time-zone issues or because they are participating in another session live, talk recordings and slides will be available online at a minimum after the live presentation (and in many cases before as well), and questions may be submitted in advance on session-specific discussion boards and answered live in session with the usual visual aids if desired.

<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/ceby/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>

Please Note: The EMNLP registration system is not currently connected to the underline site as we are still in the process of building out EMNLP 2021. You will receive access instructions from underline the week of November 1st. 

Access is given only to EMNLP upon registration, if you have not registered please do so [here](https://2021.emnlp.org/registration).

Registered attendees will receive access the week of November 1st.

EMNLP 2021

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible.

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*





<br>

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

Recent advances show that the world knowledge in the Instruction Fine-Tuning (IFT) dataset, which is incompatible with LLMs' internal knowledge, can greatly hurt the IFT performance. However, the effective integration and balancing of the internal knowledge of LLMs, acquired during pre-training, with existing IFT datasets remains a largely underexplored area of research. To address this gap, this work introduces NILE, a novel framework to optimize the effectiveness of IFT by adjusting IFT datasets through carefully aligning the world and internal knowledge. NILE employs a three-stage pipeline to effectively quantify and adjust consistency with the internal knowledge of target LLMs. Our analysis provides compelling evidence that balancing such consistency with pre-trained internal knowledge is pivotal for unleashing LLM potential, and confirms that NILE can systematically contribute to these substantial performance improvements. Experimental results demonstrate that NILE-aligned IFT datasets sharply boost LLM performance across multiple LLM ability evaluation datasets, achieving up to 66.6% gain on Arena-Hard and 68.5% on Alpaca-Eval V2.

NILE: Internal Consistency Alignment in Large Language Models

Large Language Models (LLMs) are increasingly used to generate synthetic textual data for training smaller specialized models. However, a comparison of various generation strategies for low-resource language settings is lacking. While various prompting strategies have been proposed—such as demonstrations, label-based summaries, and self-revision—their comparative effectiveness remains unclear, especially for low-resource languages. In this paper, we systematically evaluate the performance of these generation strategies and their combinations across 11 typologically diverse languages, including several extremely low-resource ones. Using three NLP tasks and four open-source LLMs, we assess downstream model performance on generated versus gold-standard data. Our results show that strategic combinations of generation methods — particularly target-language demonstrations with LLM-based revisions — yield strong performance, narrowing the gap with real data to as little as 5% in some settings. We also find that smart prompting techniques can reduce the advantage of larger LLMs, highlighting efficient generation strategies for synthetic data generation in low-resource scenarios with smaller models.

A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages

Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure (\textit{on-premises}) to safeguard private data and enable customization. However, vulnerabilities in local environments can lead to unauthorized access and potential model theft. To address this, prior research on small models has explored securing only the output layer within hardware-secured devices to balance model confidentiality and customization. Yet this approach fails to protect LLMs effectively. In this paper, we discover that (1) query-based distillation attacks targeting the secured top layer can produce a functionally equivalent replica of the victim model; (2) securing the same number of layers, bottom layers before a transition layer provide stronger protection against distillation attacks than top layers, with comparable effects on customization performance; and (3) the number of secured layers creates a trade-off between protection and customization flexibility. Based on these insights, we propose SOLID, a novel deployment framework that secures a few bottom layers in a secure environment and introduces an efficient metric to optimize the trade-off by determining the ideal number of hidden layers. Extensive experiments on five models (1.3B to 70B parameters) demonstrate that SOLID outperforms baselines, achieving a better balance between protection and downstream customization.

A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality

Large Language Models (LLMs) with extended context lengths face significant computational challenges during the pre-filling phase, primarily due to the quadratic complexity of self-attention. Existing methods typically employ dynamic pattern matching and block-sparse low-level implementations. However, their reliance on local information for pattern identification fails to capture global contexts, and the coarse granularity of blocks leads to persistent internal sparsity, resulting in suboptimal accuracy and efficiency. To address these limitations, we propose \textbf{AnchorAttention}, a difference-aware, dynamic sparse attention mechanism that efficiently identifies critical attention regions at a finer stripe granularity while adapting to global contextual information, achieving superior speed and accuracy. AnchorAttention comprises three key components: (1) \textbf{Pattern-based Anchor Computation}, leveraging the commonalities present across all inputs to rapidly compute a set of near-maximum scores as anchor; (2) \textbf{Difference-aware Stripe Sparsity Identification}, performing difference-aware comparisons with anchor to quickly obtain discrete coordinates of significant regions in a stripe-like sparsity pattern; (3) \textbf{Fine-grained Sparse Computation}, replacing the traditional contiguous loading strategy with a discrete key-value loading approach to maximize sparsity rates while preserving hardware computational potential. Additionally, we integrate the identification strategy into a single operator to maximize parallelization potential. With its finer-grained sparsity strategy, \textbf{AnchorAttention} achieves higher sparsity rates at the same recall level, significantly reducing computation time. Compared to previous state-of-the-art methods, at a text length of 128k, it achieves a speedup of 1.44times while maintaining higher recall rates.

AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity

Fine-tuning pre-trained large language models (LLMs) on downstream tasks has achieved significant success across various domains. However, as model sizes grow, traditional first-order fine-tuning algorithms incur substantial memory overhead due to the need for activation storage for back-propagation (BP). The BP-free Memory-Efficient Zeroth-Order Optimization (MeZO) method estimates gradients through finite differences, avoiding the storage of activation values, and has been demonstrated as a viable approach for fine-tuning large language models. This work proposes the Multiple-query Memory Efficient Zeroth-Order (MUZO) method, which is based on variance-reduced multiple queries to obtain the average of gradient estimates. When combined with Adam optimizer, MUZO-Adam demonstrates superior performance in fine-tuning various LLMs. Furthermore, we provide theoretical guarantees for the convergence of the MUZO-Adam optimizer. Extensive experiments empirically demonstrate that MUZO-Adam converges better than MeZO-SGD and achieves near first-order optimizer performance on downstream classification, multiple-choice, and generation tasks.

MUZO: Leveraging Multiple Queries and Momentum for Zeroth-Order Fine-Tuning of Large Language Models

Vision Language Models (VLMs) face significant computational challenges with long-form videos due to attention mechanisms' quadratic complexity. We propose Language-Guided Temporal Token Pruning (LGTTP), which extracts temporal cues from queries to adaptively assign pruning rates across video frames, preserving contextual continuity while reducing computational overhead. Unlike existing methods that apply uniform token pruning or disruptive keyframe selection, LGTTP maintains higher token density in temporally relevant segments. Our model-agnostic approach integrates with TimeChat and LLaVA-Video architectures, demonstrating substantial efficiency gains across diverse benchmarks. Experiments show LGTTP reduces computation by 65% while preserving 97-99% of original performance. On highlight detection, LGTTP achieves +9.5% HIT@1 on QVHighlights compared to baseline methods, and for temporal grounding, it maintains 99.6% of original R@1 on Charades-STA. LGTTP shows particular strength for queries with explicit temporal markers while remaining effective for general video understanding tasks.

Language-Guided Temporal Token Pruning for Efficient VideoLLM Processing

Large Language Model Unlearning (LLMU) is a promising way to remove private or sensitive information from large language models. However, the comprehensive evaluation of LLMU remains underexplored. The dominant deterministic evaluation can yield overly optimistic assessments of unlearning efficacy. To mitigate this, we propose a Fully Probabilistic Evaluation (FPE) framework that incorporates input and output distributions in LLMU evaluation. FPE obtains a probabilistic evaluation result by querying unlearned models with various semantically similar inputs and multiple sampling attempts. We introduce an Input Distribution Sampling method in FPE to select high-quality inputs, enabling a stricter measure of information leakage risks. Furthermore, we introduce a Contrastive Embedding Loss (CEL) to advance the performance of LLMU. CEL employs contrastive learning to distance latent representations of unlearned samples from adaptively clustered contrast samples while aligning them with random vectors, leading to improved efficacy and robustness for LLMU. Our experiments show that FPE uncovers more unlearned information leakage risks than prior evaluation methods, and CEL improves unlearning effectiveness by at least 50.1% and robustness by at least 37.2% on Llama-2-7B while retaining high model utility.

A Fully Probabilistic Perspective on Large Language Model Unlearning: Evaluation and Optimization

Recent advances in reasoning models have demonstrated significant improvements in accuracy, particularly for complex tasks such as mathematical reasoning, by employing detailed and comprehensive reasoning processes. However, generating these lengthy reasoning sequences is computationally expensive and time-consuming. To address this inefficiency, we leverage the inherent parallelizability of certain tasks to accelerate the reasoning process. Specifically, when multiple parallel reasoning branches exist, we decode multiple tokens per step using a specialized attention mask, processing them within a single sequence, avoiding additional memory usage. Experimental results show that our method achieves over 100% speedup in decoding time while maintaining the answer quality.

Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence

Direct Preference Optimization (DPO) is a widely used reinforcement learning from human feedback (RLHF) method across various domains. The study of token importance has attracted widespread attention in DPO. Researchers have found that token importance is crucial for improving the effectiveness of DPO. It is observed that identical or semantically similar content (defined as ambiguous content) frequently appears within the preference pairs. We hypothesize that the presence of ambiguous content during DPO training may introduce ambiguity, thereby limiting further improvements in alignment. Through mathematical analysis and proof-of-concept experiments, we reveal that ambiguous content may potentially introduce ambiguities, thereby degrading performance. To address this issue, we introduce Ambiguity Awareness Optimization (AAO), a simple yet effective approach that automatically re-weights ambiguous content to reduce ambiguities by calculating semantic similarity from preference pairs. Through extensive experiments, we demonstrate that AAO consistently and significantly surpasses state-of-the-art approaches in performance, without markedly increasing response length, across multiple model scales and widely adopted benchmark datasets, including AlpacaEval 2, MT-Bench, and Arena-Hard. Specifically, AAO outperforms DPO by up to 8.9 points on AlpacaEval 2 and achieves an improvement of by up to 15.0 points on Arena-Hard.

Ambiguity Awareness Optimization: Towards Semantic Disambiguation for Direct Preference Optimization

LLM-powered conversational assistants are often deployed in a one-size-fits-all manner, which fails to accommodate individual user preferences. Recently, LLM personalization -- tailoring models to align with specific user preferences -- has gained increasing attention as a way to bridge this gap. In this work, we specifically focus on a practical yet challenging setting where only a small set of preference annotations can be collected per user -- a problem we define as Personalized Preference Alignment with Limited Data (PPALLI). To support research in this area, we introduce two datasets -- DnD and ELIP -- and benchmark a variety of alignment techniques on them. We further propose FaST, a highly parameter-efficient approach that leverages high-level features automatically discovered from the data, achieving the best overall performance.

Downloads

Next from EMNLP 2025

NILE: Internal Consistency Alignment in Large Language Models

Similar lecture

Understanding and Overcoming the Challenges of Efficient Transformer Quantization