United States

As Large Language Models (LLMs) serve a global audience, alignment must transition from enforcing universal consensus to respecting cultural pluralism. We demonstrate that dense models, when forced to fit conflicting value distributions, suffer from Mean Collapse, converging to a generic average that fails to represent diverse groups. We attribute this to Cultural Sparsity, where gradient interference prevents dense parameters from spanning distinct cultural modes. To resolve this, we propose CuMA (Cultural Mixture of Adapters), a framework that frames alignment as a conditional capacity separation problem. By incorporating demographic-aware routing, CuMA internalizes a Latent Cultural Topology to explicitly disentangle conflicting gradients into specialized expert subspaces. Extensive evaluations on WorldValuesBench, Community Alignment, and PRISM demonstrate that CuMA achieves competitive performance, outperforming both dense baselines and semantic-only MoEs. Our analysis confirms that CuMA effectively mitigates mean collapse and preserves cultural diversity. Our code is available at https://github.com/Throll/CuMA.

ACL 2026

CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters

### 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**. 

ACL 2025

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

technical paper

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields 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.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>

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 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/acl2026

Registration Required

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

This paper notices that while symbolic instruction and neural parameters play different roles on steering LLMs' behavior, both instructions and parameters are the compression of task data, they are supposed be strongly correlated and can be learned to predict one from the other. Therefore, This paper proposes a novel neural network framework, SHIP (\textbf{Sh}uttle between the \textbf{I}nstructions and the \textbf{P}arameters), to model and learn the bi-directional mappings between the instructions and the parameters of LLMs. We verify that SHIP can effectively map one of the instructions/parameters to the other by evaluating it on the tasks of instruction deduction and induction. The results show that SHIP performs better than existing baseline methods in terms of deductive capabilities while significantly surpassing them in inductive capabilities. Moreover, SHIP can effectively combine the two mapping processes to perform excellent inductive reasoning. We further discuss how the latent fusing methods and latent dimensions affect SHIP's performance, and show SHIP can effectively generalize with pre-training. The code and data for this paper are released at https://anonymous.4open.science/r/Shuttle-Between-Instructions-Parameters

Shuttle Between Symbolic Instructions and Neural Parameters of Large Language Models

Agentic search augments large language models (LLMs) with external knowledge through reinforcement learning. However, existing approaches suffer from blind reliance on noisy retrieval and hallucination when both parametric and external knowledge fail—reflecting a lack of calibration regarding the model's knowledge boundary. We propose Knowledge boundary Policy Optimization (KbPO), a reinforcement learning framework that explicitly aligns retrieval decisions with quantified knowledge states. KbPO introduces: (1) a semantic stability metric to delineate reliable parametric knowledge; (2) a four-quadrant taxonomy synthesising internal certainty with retrieval quality; and (3) a quadrant-based reward mechanism incentivising calibrated behaviour. We further adopt an iterative query evolution pipeline to construct boundary-probing training samples. Experiments on ten benchmarks demonstrate that KbPO outperforms strong baselines while exhibiting reduced hallucination rates.

Trust Within? Seek Beyond? Knowledge Boundary Aware Policy Optimization for Agentic Search

Optimizing distributed training strategies for large-scale deep learning models remains a critical challenge in both industry and academia, demanding extensive domain expertise and manual tuning. Existing automated distributed training frameworks are plagued by over-reliance on prior profiling, poor generalization across models/hardware, and scalability constraints stemming from vast search spaces, impeding real-world applicability. To address these challenges, we propose OptiCo, a model-driven multi-agent framework that leverages Large Language Models (LLMs) to enable automatic and explainable distributed training strategy configuration. OptiCo orchestrates a team of reasoning-driven agents, through a shared Global Message Pool facilitating persistent memory and coordination. By employing inception prompting and Chain-Of-Thought (COT) reasoning, agents iteratively refine configurations, detect bottlenecks, analyze failures, and optimize resource utilization. Evaluated across 25+ configurations spanning diverse model architectures, GPU types and scales, OptiCo outperforms expert-designed strategies within 20 iterations, achieving an average performance improvement of 1.84%, with gains ranging from 0.08% to 8.65%. The source codes are avaiable at https://github.com/TangZhe96/OptiCo-public.

OptiCo: Adaptive Distributed Training Optimization via Collaborative Agent Reasoning

LLMs often fail in hardware vulnerability detection due to the intrinsic semantic concurrency of HDLs (Hardware Description Language), where vulnerabilities arise from the interaction of multiple concurrent execution statements rather than a single sequential execution path. To address the problem, we propose VerilogLAVD, a LLM-Aided Vulnerability Detection framework by generating executable Traversal Detection Patterns (TDPs), i.e. the rules describing how to find the evidence of vulnerabilities in Verilog HDL. We first introduce a Unified Verilog Property Graph (VeriPG) that explicitly models parallel semantics by combining AST, CFG, and DDG. Furthermore, a semantic validation mechanism is designed to constrain and filter the LLM-generated TDPs. By executing these validated TDPs on VeriPG, our method produces stable and deterministic detection results. Experiments demonstrate that VerilogLAVD improves the F1 score by 133% compared to LLM-based methods. Furthermore, the framework successfully identifies real-world hardware vulnerabilities in open-source hardware design repositories.

VerilogLAVD: LLM-Aided Pattern Generation for Verilog CWE Detection

Dynamic topic modeling aims to capture topic evolution from temporal text corpora. However, existing methods face two major challenges when applied to short texts: semantic ambiguity and interpretation ambiguity. Semantic ambiguity arises from the sparsity of short texts and the neglect of temporal semantic shifts. Interpretation ambiguity refers to the latent topics that lack human-understandable descriptions. In this work, we propose a novel Dual-View representation learning-based Interpretable short text Dynamic Topic Model (DVI-DTM). To address semantic ambiguity, the Dual-View Representation Learning module is presented to learn robust document-topic distributions by aligning temporal-aware term view and sentence view representations of short texts. To tackle interpretation ambiguity, we introduce a GEA Topic Refiner that leverages LLM agents to generate topic descriptions and refine document-topic distributions through collaborative semantic reasoning. Furthermore, a Dual-Factor Ranking module is designed to capture the topic evolution through semantic relevance and temporal uniqueness. Comprehensive experiments demonstrate that DVI-DTM outperforms the state-of-the-art baselines in topic alignment and dynamic topic quality metrics while producing highly interpretable topic descriptions.

DVI-DTM: Dual-View Representation Learning for Interpretable Short Text Dynamic Topic Modeling

Block-wise discrete diffusion offers an attractive balance between parallel generation and causal dependency modeling, making it a promising backbone for vision-language modeling. However, its practical adoption has been limited by high training cost, slow convergence, and instability, which have so far kept it behind strong autoregressive (AR) baselines. We present \textbf{SDAR-VL}, the first systematic application of block-wise discrete diffusion to large-scale vision-language understanding (VLU), together with an \emph{integrated framework for efficient and stable training}. This framework unifies three components: 1) \textbf{Asynchronous Block-wise Noise Scheduling} to diversify supervision within each batch; 2) \textbf{Effective Mask Ratio Scaling} for unbiased loss normalization under stochastic masking; and 3) a \textbf{Progressive Beta Noise Curriculum} that increases effective mask coverage while preserving corruption diversity. Experiments on 21 single-image, multi-image, and video benchmarks show that SDAR-VL consistently improves \emph{training efficiency}, \emph{convergence stability}, and \emph{task performance} over conventional block diffusion. On this evaluation suite, SDAR-VL sets a new state of the art among diffusion-based vision-language models and, under matched settings, matches or surpasses strong AR baselines such as LLaVA-OneVision as well as the global diffusion baseline LLaDA-V, establishing block-wise diffusion as a practical backbone for VLU.

SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding

Current LLM role-playing systems model persona as a monolithic, static attribute, conflating identity consistency with emotional rigidity. This leads to either robotic repetition or catastrophic persona drift under sustained interaction. We introduce Dynamic Persona Coherence, a framework that decouples Identity-Layer Stability (time-invariant traits) from Adaptive-Layer Appropriateness (history-dependent psychological evolution). We operationalize this through the L/M/S Psychological State Model, which represents persona dynamics across long-term identity, mid-term meaning/stress accumulation, and short-term affect. On top of this state representation, a closed-loop alignment system comprising an automated evaluator (Persona Consistency Critic, PCC), a selective repository (Persona Case Repository, PCR), and a trajectory-adjusting corrector (Persona Drift Suppressor, PDS) enables autonomous coherence repair. Experiments on GPT-4o, Claude-3.5-Sonnet, and DeepSeek-V3.2 demonstrate consistent improvements (+16–84% PCC gains).

Beyond Static Persona Consistency: Dynamic Persona Coherence in LLM Role-Playing

Large Language Models (LLMs) achieve strong program repair performance but often suffer from over-editing, where excessive modifications overwrite correct code and hinder bug localization. We systematically quantify its impact and introduce precise repair task, which maximizes reuse of correct code while fixing only buggy parts. Building on this insight, we propose PRepair, a framework that mitigates over-editing and improves repair accuracy. PRepair has two components: Self-Breaking, which generates diverse buggy programs via controlled bug injection and min–max sampling, and Self-Repairing, which trains models with Edit-Aware Group Relative Policy Optimization (EA-GRPO) using an edit-aware reward to encourage minimal yet correct edits. Experiments show that PRepair improves repair precision by up to 31.4% under $\mathrm{fix}_1@1$, a metric that jointly considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing, demonstrating its potential for precise and practical code repair.

QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization

Credit assignment is a fundamental challenge in cooperative multi-agent reinforcement learning, particularly in embodied AI settings characterized by limited and delayed feedback as well as dynamically changing numbers of active agents. We propose MARS-RA, a framework that reformulates credit assignment as a rank aggregation problem using contribution-based pairwise comparisons among agents generated by large multimodal models. This shift from absolute to relative estimation ensures robustness against noise and dynamic agent participation, converting comparison results into contribution scores for potential-based reward shaping. We provide theoretical justification for the convergence and robustness of the proposed framework, and show that Shapley values can be used as an interpretive reference. Experimental results on challenging tasks of different types indicate that MARS-RA can guide agents toward effective cooperation.

MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation

Guqin (古琴) Jianzi (減字) is an open and freely compositional tablature system that encodes performance actions rather than acoustic outcomes. Its automatic recognition remains largely unexplored, as conventional OCR assumes a closed and enumerable glyph set and struggles with Jianzi’s unbounded composition and manuscript-level variability.

We introduce Zero-shot Jianzi Recognition, which formulates Jianzi recognition as vision-to-sequence prediction of canonical component sequences under a zero-shot split. To enable scalable supervision, we construct Synthetic-JZ from aligned online composition metadata. We then synthesize manuscript-like training images via component-wise style recomposition and manuscript-domain noise modeling, and fine-tune a vision–language model for end-to-end component sequence recognition. At inference time, a lightweight legality-guided correction module re-ranks decoding candidates, suppressing structural hallucinations without modifying the backbone.

Experiments on two benchmarks show that our method achieves 63.02% sequence accuracy on Real-JZ, our manually annotated real-world Jianzi benchmark, surpassing Gemini-3-Pro by 35.11%. This result highlights the feasibility of reliable automated Jianzi recognition and its potential for large-scale digitization of historical Guqin Jianzi Pu manuscripts.

Downloads

Next from ACL 2026

Shuttle Between Symbolic Instructions and Neural Parameters of Large Language Models

Similar lecture

Cultural Learning-Based Culture Adaptation of Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES