United States

Natural language to SQL (NL2SQL) provides an intuitive interface for querying structured data, yet real user questions are often noisy, ambiguous, and weakly grounded to database semantics.
As a result, token-level schema linking and single-pass SQL decoding can be brittle: small misunderstandings in language or schema grounding may propagate into incorrect generation.
We present \textit{QBridge}, an agentic, feedback-driven NL2SQL framework based on a \textit{Refined Gold Query Paradigm}, which bridges natural language and SQL via \textit{Gold Query}---a structured, SQL-aligned intermediate representation.
A core insight of \textit{QBridge} is \textit{Distilled Back-Translation (DBT)} for SL-independent rewriting.
DBT converts SQL-grounded supervision into \emph{execution-verified} Gold-Query-style rewrites from a teacher model, and distills a lightweight, plug-and-play rewriter that generates schema-aware rewrites without requiring explicit schema linking at inference.
\textit{QBridge} then (i) verifies and conservatively refines the rewrite into a high-fidelity \textit{Refined Gold Query}, and (ii) refines the generated SQL with dual feedback from execution validity and semantic consistency, enabling interpretable self-correction while remaining compatible with diverse SQL backbones.
Extensive experiments on Spider, BIRD, and three robustness variants demonstrate that \textit{QBridge} consistently improves zero-shot NL2SQL, outperforming strong prompting and agentic baselines while showing strong robustness and generalization. Code and data are available at \url{https://github.com/WannaBSteve/QBridge}.

ACL 2026

QBridge: Bridging Natural Language and SQL via Gold Query Rewriting with Agentic Refinement

#### *Message from the General Chair, Aline Villavicencio*
I’m delighted and honoured to welcome you to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), taking place in the beautiful city of Rabat, in Morocco, in March 24-29, 2026. EACL is the flagship European conference of the Association and EACL 2026 proudly continues our field’s tradition of excellence in scholarship, innovation, and inclusivity. I am deeply grateful to the many volunteers whose dedication, generosity, and tireless efforts have made this conference possible.
For the first time EACL is being hosted in the African continent. This is an important milestone for our community, and we are grateful to our Moroccan hosts for enabling this historic moment by bringing this edition of EACL to Rabat. We are also delighted that the Second Arabic NLP School is co-located with EACL. We hope attendees enjoy this wonderful opportunity to strengthen ties with the Computational Linguistics communities across the African continent. *[Read full message](https://drive.google.com/file/d/14NlmHvwM6fPJuMmOvVh7K0vtQbEyv3SZ/view?usp=sharing)*<br><br>

<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://underline.io/events/522/reception','_blank')">Go to Workshops and Tutorials Program</button></html>
<br><br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to EACL 2026". 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 are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.eacl.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/eacl2026

Registration Required

EACL 2026

Welcome to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL). EACL 2026 will be held in Rabat, Morocco, from March 24–29, 2026. 

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. <br>
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) <br><br><br>
<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>
<br><br><br><br>

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

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

Large language models and agents have achieved remarkable progress in code generation. However, existing benchmarks focus on isolated function/class-level generation (e.g., ClassEval) or modifications to existing codebases (e.g., SWE-Bench), neglecting complete microservice repository generation that reflects real-world 0-to-1 development workflows. To bridge this gap, we introduce RepoGenesis, the first multilingual benchmark for repository-level end-to-end web microservice generation, comprising 106 repositories (60 Python, 46 Java) across 18 domains and 11 frameworks, with 1,258 API endpoints and 2,335 test cases verified through a ``review-rebuttal'' quality assurance process. We evaluate open-source agents (e.g., DeepCode) and commercial IDEs (e.g., Cursor) using Pass@1, API Coverage (AC), and Deployment Success Rate (DSR). Results reveal that despite high AC (up to 73.91%) and DSR (up to 100%), the best-performing system achieves only 23.67% Pass@1 on Python and 21.45% on Java, exposing deficiencies in architectural coherence, dependency management, and cross-file consistency. Notably, RepoGenesis-8B, fine-tuned on RepoGenesis (train), achieves performance comparable to GPT-5 mini, demonstrating the quality of RepoGenesis for advancing microservice generation. We release our benchmark at \url{https://github.com/pzy2000/RepoGenesis}.

RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository

Visual token pruning methods effectively mitigate the quadratic computational growth caused by processing high-resolution images and video frames in vision-language models (VLMs). However, existing approaches rely on predefined pruning configurations without determining whether they achieve computation-performance optimality. In this work, we introduce , a novel framework that formulates visual token pruning as a Pareto configuration optimization problem to automatically identify optimal configurations. Our approach employs continuous relaxation and straight-through estimators to enable gradient-based search, solved via the Augmented Lagrangian method. Extensive experiments across 8 visual benchmarks demonstrate that effectively approximates the empirical Pareto frontier obtained through grid search and generalizes well across various pruning methods and VLM architectures. Furthermore, through learnable kernel functions, we investigate layer-wise pruning patterns and reveal that multi-step progressive pruning captures VLMs' hierarchical compression structure, achieving superior accuracy-efficiency trade-offs compared to single-layer approaches.

VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models

While critical for alignment, Supervised Fine-Tuning (SFT) incurs the risk of catastrophic forgetting, yet the layer-wise emergence of instruction-following capabilities remains elusive. We investigate this mechanism via a comprehensive analysis utilizing information-theoretic, geometric, and optimization metrics across model scales (1B-32B). Our experiments reveal a distinct depth-dependent pattern: middle layers (20%-80%) are stable, whereas final layers exhibit high sensitivity. Leveraging this insight, we propose Mid-Block Efficient Tuning, which selectively updates these critical intermediate layers. Empirically, our method outperforms standard LoRA up to 10.2% on GSM8K (OLMo2-7B) with reduced parameter overhead, demonstrating that effective alignment is architecturally localized rather than distributed. The code is publicly available at https://github.com/lshowway/base.

A Layer-wise Analysis of Supervised Fine-Tuning

Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal Large Language Models (MLLMs), we find that current paradigms still suffer from an important yet remain underexplored issue : editing decoupling failure, where entity-related knowledge can be updated when the model is triggered by multimodal inputs (text--image query pairs), however, it often reverts to outdated pre-edit facts when the paired inputs are split into unimodal ones. Our in-depth empirical analysis reveals that the entity knowledge in MLLMs is not stored as a unified representation, but is instead distributed across disentangled modality-specific pathways. As a result, updates biased toward multimodal queries fail to propagate effectively to unimodal circuits. To bridge this gap, we propose DECODE, which explicitly disentangles and localizes modality-specific neuron groups for targeted knowledge. Extensive experiments demonstrate that DECODE consistently achieves effective knowledge updates under different modality triggers, thereby mitigating editing decoupling failures.

Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs

When asked explicitly, a Large language model (LLM) may validate your anger—but implicitly, it may still judge that anger as inappropriate. We call this divergence the endorsement–exposure gap, and it reveals that LLMs encode hidden norms about which emotions are acceptable in which contexts. To measure these norms systematically, we introduce Feeling Rules Atlas, a benchmark of 1,320 vignettes spanning 6 institutional settings, 12 roles, 7 emotions, and 5 intensity levels. We pair the benchmark with two probes: explicit norm judgments (APPROPRIATE/INAPPROPRIATE/DEPENDS) and implicit acceptability scored by log-likelihood contrast. Across six model families, we find large cross-model variation in sanctioning thresholds and institutional "norm signatures" not reducible to overall strictness; models that appear similarly lenient explicitly can diverge sharply in implicit judgments. These results establish normative affect—context-conditioned judgments of emotional appropriateness—as a distinct alignment axis, and motivate transparent profiling of feeling rules for emotionally sensitive deployments.

Feeling Rules in Language Models: Mapping Norms of Emotional Appropriateness Across Roles, Institutions, and Intensity

Open-weight large language models (LLMs) enable broad customization, but also increase exposure to post-release misuse, including malicious fine-tuning (MFT). To mitigate this risk, many prior defenses aim to improve the robustness of open-weight models to MFT by constraining adversarial fine-tuning dynamics in parameter space or mitigating harmful information encoded in internal representations. Nevertheless, since malicious fine-tuning can still erode safety, developing robust safeguards for open-weight models that fundamentally mitigate this risk remains an open research problem. In this paper, we characterize a safety region for open-weight LLMs and propose Safety Guidance Trigger (SGT), which guides fine-tuning toward the safety manifold to preserve alignment. SGT has two stages: (1) optimizing a safety trigger that steers the base model toward safe responses and (2) training the open-weight model to align its internal features with trigger-induced safety representations. We demonstrate that SGT substantially improves robustness against malicious fine-tuning, requiring adversaries to increase their data budget significantly to compromise safety. Our analysis shows that SGT anchors model representations to a safety region, which remains stable under malicious fine-tuning.

SGT: Securing Open-Source LLMs Against Malicious Fine-tuning via Safety Guidance Trigger

While Mamba has demonstrated strong performance in language modeling, its potential as a speech self-supervised learning (SSL) model remains underexplored, with prior studies limited to isolated tasks. To address this, we explore Mamba-based HuBERT models as alternatives to Transformer-based SSL architectures. Leveraging the linear-time Selective State Space, these models enable fine-tuning on long-context ASR with significantly lower compute. Moreover, they show superior performance when fine-tuned for streaming ASR. Beyond fine-tuning, these models show competitive performance on SUPERB probing benchmarks, particularly in causal settings. Our analysis shows that they yield higher-quality quantized representations and capture speaker-related features more distinctly than Transformer-based models. These findings highlight Mamba-based SSL as a promising and complementary direction for long-sequence modeling, real-time speech modeling, and speech unit extraction. The codebase is available at https://github.com/hckuo145/Mamba-based-HuBERT.

An Exploration of Mamba for Speech Self-Supervised Models

In isolating languages such as Vietnamese, core morphological structure is encoded not by inflection but by the composition and ordering of monosyllabic morphemes, yet standard Transformer encoders largely overlook this signal. We introduce HuTieuBERT, a morpheme-aware Transformer that augments a pretrained Vietnamese encoder with two lightweight inductive biases: (i) Adaptive Boundary-Token Fusion, which integrates BMES-based morpheme boundary embeddings into token representations via a learnable gate, and (ii) a Morpheme-Aware Attention Bias, which injects a fixed structural attention matrix into early self-attention layers while minimally perturbing the pretrained attention geometry. Across a suite of Vietnamese POS, NER, and sentence-level classification benchmarks, HuTieuBERT consistently outperforms strong baselines, with the largest gains on syntactic tasks. Hyperparameter ablations show a broad regime in which structural biases improve accuracy without destabilizing representations. Applying the same design to ChineseBERT (Chinese-BERT-wwm) yields MAChineseBERT, which improves $F_{1}$ and produces more balanced tag distributions on Chinese POS and NER, suggesting that explicit morpheme-aware attention is a portable and effective strategy for modeling isolating languages.

When Morphology Hides in Plain Sight: Breaking the Isolation in Vietnamese and Beyond

Automatic soccer commentary generation aims to bridge the gap between raw visual content and professional, tactical commentary. However, existing datasets tend to produce incomplete commentary that lacks semantic richness and fails to convey the full visual information present in standard video clips. To address these limitations, we propose two manually curated datasets: SN-Short, which enhances scene-level semantic descriptions, and SN-Long, which captures event continuity for context-aware commentary.
Based on these, we design a commentary augmentation pipeline that transforms incomplete annotations into MatchText, a semantically complete and structurally standardized dataset. Leveraging this supervision, we introduce MatchAware, a generation model that incorporates contextual cues from previous events to produce coherent commentary aligned with the visual flow of the game. Experimental results show that proposed approach significantly outperforms existing baselines on the constructed datasets.

Visual and Memory–Augmented Soccer Commentary Generation

Large language models (LLMs) have recently advanced knowledge graph question answering (KGQA), but current methods tend to rely on LLM-induced type systems with inconsistent granularity, or perform multi-hop reasoning without explicit target-type constraints. We introduce OntGQA, a type-constrained KGQA framework that reasons over a relation-centric ontology graph, where each relation is labeled with its head and tail entity types to provide a stable schema backbone. Built on this graph, OntGQA adopts a planner–judge architecture with generative backoff: a type planner proposes plausible head–tail type pairs, a judge verifies retrieved candidates and their paths, and a generator is invoked only when all candidates are rejected. By constraining both endpoints of reasoning in type space, OntGQA achieves state-of-the-art performance and produces ontology-grounded reasoning chains, with substantial Hit@1 gains (87.7%→91.5% on WebQSP and 67.6%→74.6% on CWQ).

Downloads

Next from ACL 2026

RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository

Similar lecture

LitE-SQL: A Lightweight and Efficient Text-to-SQL Framework with Vector-based Schema Linking and Execution-Guided Self-Correction