Austria

One of the primary challenges in optimizing large language models (LLMs) for long-context inference lies in the high memory consumption of the Key-Value (KV) cache. Existing approaches, such as quantization, have demonstrated promising results in reducing memory usage. However, current quantization methods cannot take both effectiveness and efficiency into account. In this paper, we propose MoQAE, a novel mixed-precision quantization method via mixture of quantization-aware experts. First, we view different quantization bit-width configurations as experts and use the traditional mixture of experts (MoE) method to select the optimal configuration. To avoid the inefficiency caused by inputting tokens one by one into the router in the traditional MoE method, we input the tokens into the router chunk by chunk. Second, we design a lightweight router-only fine-tuning process to train MoQAE with a comprehensive loss to learn the trade-off between model accuracy and memory usage. Finally, we introduce a routing freezing (RF) and a routing sharing (RS) mechanism to further reduce the inference overhead. Extensive experiments on multiple benchmark datasets demonstrate that our method outperforms state-of-the-art KV cache quantization approaches in both efficiency and effectiveness.

ACL 2025

MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts

routing freezing and routing sharing

quantization-aware experts

mixed-precision quantization

llm long-context inference

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

poster

Retrieval-Augmented Generation (RAG) mitigates the hallucination problem of Large Language Models (LLMs) by incorporating external knowledge. Recursive summarization constructs a hierarchical summary tree by clustering text chunks, integrating information from multiple parts of a document to provide evidence for abstractive questions involving multi-step reasoning. However, summary trees often contain a large number of redundant summary nodes, which not only increase construction time but may also negatively impact question answering. Moreover, recursive summarization is not suitable for all types of questions. We introduce DTCRS, a method that dynamically generates summary trees based on document structure and query semantics. DTCRS determines whether a summary tree is necessary by analyzing the question type. It then decomposes the question and uses the embeddings of sub-questions as initial cluster centers, reducing redundant summaries while improving the relevance between summaries and the question. Our approach significantly reduces summary tree construction time and achieves substantial improvements across three QA tasks. Additionally, we investigate the applicability of recursive summarization to different question types, providing valuable insights for future research.

DTCRS: Dynamic Tree Construction for Recursive Summarization

AI support of collaborative interactions entails mediating potential misalignment between interlocutor beliefs. Common preference alignment methods like DPO excel in static settings, but struggle in dynamic collaborative tasks where the explicit signals of interlocutor beliefs are sparse and skewed. We propose the Frictional Agent Alignment Framework (FAAF), to generate precise, context-aware "friction" that prompts for deliberation and re-examination of existing evidence. FAAF’s two-player objective decouples from data skew: a frictive-state policy identifies belief misalignments, while an intervention policy crafts collaborator-preferred responses. We derive an analytical solution to this objective, enabling training a single policy via a simple supervised loss. Experiments on three benchmarks show FAAF outperforms competitors in producing concise, interpretable friction and in OOD generalization. By aligning LLMs to act as adaptive "thought partners"---not passive responders---FAAF advances scalable, dynamic human-AI collaboration. Our code and data can be found at https://github.com/csu-signal/FAAF_ACL.

Frictional Agent Alignment Framework: Slow Down and Don’t Break Things

While great success has been achieved in building vision models with Contrastive Language-Image Pre-training (CLIP) over Internet-scale image-text pairs, building transferable Graph Neural Networks (GNNs) with CLIP pipeline is challenging because of the scarcity of labeled data and text supervision, different levels of downstream tasks, and the conceptual gaps between domains. In this work, to address these issues, we propose a multi-modal prompt learning paradigm to effectively adapt pre-trained GNN to downstream tasks and data, given only a few semantically labeled samples, each with extremely weak text supervision. Our new paradigm embeds the graphs directly in the same space as the Large Language Models (LLMs) by learning both graph prompts and text prompts simultaneously. We demonstrate the superior performance of our paradigm in few-shot, multi-task-level, and cross-domain settings. Moreover, we build the first CLIP-style zero-shot classification prototype that can generalize GNNs to unseen classes with extremely weak text supervision.

Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?

Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences. However, effectively aligning LLMs with diverse human preferences remains a significant challenge, particularly when they are conflict. To address this issue, we frame human value alignment as a multi-objective optimization problem, aiming to maximize a set of potentially conflicting objectives. We introduce Gradient-Adaptive Policy Optimization (GAPO), a novel fine-tuning paradigm that employs multiple-gradient descent to align LLMs with diverse preference distributions. GAPO adaptively rescales the gradients for each objective to determine an update direction that optimally balances the trade-offs between objectives. Additionally, we introduce P-GAPO, which incorporates user preferences across different objectives and achieves Pareto solutions that better align with the user's specific needs.

Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models

This paper introduces UoRA, a novel parameter-efficient fine-tuning (PEFT) approach for large language models (LLMs). UoRA achieves state-of-the-art efficiency by leveraging a low-rank approximation method that reduces the number of trainable parameters without compromising performance. Unlike existing methods such as LoRA and VeRA, UoRA employs a re-parametrization mechanism that eliminates the need to adapt frozen projection matrices while maintaining shared projection layers across the model. This results in halving the trainable parameters compared to LoRA and outperforming VeRA in computation and storage efficiency. Comprehensive experiments across various benchmarks demonstrate UoRA’s superiority in achieving competitive fine-tuning performance with minimal computational overhead. We demonstrate its performance on GLUE and E2E benchmarks and is effectiveness in instruction-tuning large language models and image classification models. Our contributions establish a new paradigm for scalable and resource-efficient fine-tuning of LLMs.

UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large Models

In this paper, we investigate the retrieval-augmented generation (RAG) based on Knowledge Graphs (KGs) to improve the accuracy and reliability of Large Language Models (LLMs). Recent approaches suffer from insufficient and repetitive knowledge retrieval, tedious and time-consuming query parsing, and monotonous knowledge utilization. To this end, we develop a Hypothesis Knowledge Graph Enhanced (HyKGE) framework, which leverages LLMs' powerful reasoning capacity to compensate for the incompleteness of user queries, optimizes the interaction process with LLMs, and provides diverse retrieved knowledge. Specifically, HyKGE explores the zero-shot capability and the rich knowledge of LLMs with Hypothesis Outputs to extend feasible exploration directions in the KGs, as well as the carefully curated prompt to enhance the density and efficiency of LLMs' responses. Furthermore, we introduce the HO Fragment Granularity-aware Rerank Module to filter out noise while ensuring the balance between diversity and relevance in retrieved knowledge. Experiments on two Chinese medical multiple-choice question datasets and one Chinese open-domain medical Q&A dataset with two LLM turbos demonstrate the superiority of HyKGE in terms of accuracy and explainability. Code is available at https://github.com/Artessay/HyKGE.

HyKGE: A Hypothesis Knowledge Graph Enhanced RAG Framework for Accurate and Reliable Medical LLMs Responses

Due to the demand for efficient fine-tuning of large language models, Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tuning methods. Nevertheless, while LoRA improves efficiency, there remains room for improvement in accuracy. Herein, we adopt a novel perspective to assess the characteristics of LoRA ranks. The results reveal that different ranks within the LoRA modules not only exhibit varying levels of importance but also evolve dynamically throughout the fine-tuning process, which may limit the performance of LoRA. Based on these findings, we propose BeamLoRA, which conceptualizes each LoRA module as a beam where each rank naturally corresponds to a potential sub-solution, and the fine-tuning process becomes a search for the optimal sub-solution combination. BeamLoRA dynamically eliminates underperforming sub-solutions while expanding the parameter space for promising ones, enhancing performance with a fixed rank. Extensive experiments across three base models and 12 datasets spanning math reasoning, code generation, and commonsense reasoning demonstrate that BeamLoRA consistently enhances the performance of LoRA, surpassing the other baseline methods.

BeamLoRA: Beam-Constraint Low-Rank Adaptation

Phonetic transcription requires significant time and expert training. Automated, state-of-the-art text-dependent methods still involve substantial pre-training annotation labor and may not generalize to multiple languages. Hallucination of speech amid silence or non-speech noise can also plague these methods, which fall short in real-time applications due to post hoc whole-phrase evaluation. This paper introduces Phonotomizer, a compact, unsupervised, online training approach to automatic, multilingual phonetic segmentation, a critical first stage in transcription. Unlike prior approaches, Phonotomizer trains on raw sound files alone and can modulate computational exactness. Preliminary evaluations on Irish and Twi, two underrepresented languages, exhibit segmentation comparable to current forced alignment technology, reducing acoustic model size and minimizing training epochs.

Phonotomizer: A Compact, Unsupervised, Online Training Approach to Real-Time, Multilingual Phonetic Segmentation

Speculative decoding (SD) has been demonstrated as an effective technique for lossless LLM inference acceleration.
Retrieval-based SD methods, one kind of model-free method, have yielded promising speedup, but they often rely on single retrieval resources, inefficient retrieval methods, and are constrained to certain tasks. This paper presents a novel retrieval-based speculative decoding method that adapts the suffix automaton (SAM) for efficient and accurate draft generation by utilizing the generating text sequence and static text corpus. Unlike existing $n$-gram matching methods, SAM-Decoding finds the exact longest suffix match, achieving an average time complexity of O(1) per generation step of SAM update and suffix retrieval.
It can also integrate with existing methods, adaptively selecting a draft generation strategy based on match length to generalize to broader domains. Extensive experiments on Spec-Bench show that our method is $18$\% faster than other retrieval-based SD methods. Additionally, when combined with advanced EAGLE-2, it provides an additional speedup of $3.28$\% -- $11.13$\% across various-sized LLM backbones.

SAM Decoding: Speculative Decoding via Suffix Automaton

Training Large Language Models (LLMs) with synthetic data is a prevalent practice in code generation. A key approach is self-training, where LLMs are iteratively trained on self-generated correct code snippets. In this case, the self-generated codes are drawn from a conditional distribution, conditioned on a specific seed description. However, the seed description is not the only valid representation that aligns with its intended meaning. With all valid descriptions and codes forming a joint space, codes drawn from the conditional distribution would lead to an underrepresentation of the full description-code space. As such, we propose Gibbs Fine-Tuning (GiFT), a novel self-training method inspired by Gibbs sampling. GiFT allows self-generated data to be drawn from the marginal distribution of the joint space, thereby mitigating the biases inherent in conditional sampling. We provide a theoretical analysis demonstrating the potential benefits of fine-tuning LLMs with code derived from the marginal distribution. Furthermore, we propose a perplexity-based code selection method to mitigate the imbalanced long-tail distribution of the self-generated codes. Empirical evaluation of two LLMs across four datasets demonstrates that GiFT achieves superior performance, particularly on more challenging benchmarks. Source code is available at \url{https://github.com/Alex-HaochenLi/GiFT}.

Downloads

Next from ACL 2025

DTCRS: Dynamic Tree Construction for Recursive Summarization

Similar lecture

Accurate KV Cache Quantization with Outlier Tokens Tracing