United States

Industrial Retrieval-Augmented Generation (RAG) systems depend on optical character recognition (OCR) to transform visual documents into text. Existing OCR benchmarks rely on character-level metrics, which inadequately measure downstream RAG effectiveness under real-world conditions. We introduce an OCR benchmark for industrial RAG systems covering 11 challenging document types, including extreme layouts, high-resolution pages, complex or watermarked backgrounds, historical documents with non-standard reading orders, visually decorated text, and documents containing tables and mathematical formulas. Evaluating recent SOTA OCR models under a controlled OCR-first RAG pipeline shows clear performance degradation on realistic industrial documents despite strong conventional benchmark scores. We find that high OCR accuracy does not necessarily translate into strong downstream RAG performance: structural and semantic errors can cause substantial retrieval failures even when WER/CER remains low. Further analysis shows that this mismatch is category-dependent, arises through both retrieval-side and downstream generation-side failures, and remains stable across representative OCR-first pipeline choices.

ACL 2026

When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation

### 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.

Knowledge Graph–based Retrieval-Augmented Generation (KG-RAG) enables natural language interaction with structured enterprise knowledge, yet existing agentic approaches that perform well on public benchmarks often fail to generalize to real-world enterprise Knowledge Graphs (KGs), which are dense, schema-driven, and operationally constrained. To address these limitations, we propose SCAIR (Schema-Conditioned Agentic Iterative Reasoning), a training-free framework that integrates structured planning with controlled iterative reasoning by injecting schema-conditioned structural priors and enforcing schema-aware traversal during multi-hop reasoning. Experiments on an enterprise-oriented benchmark constructed from a real-world Configuration Management DataBase (CMDB) demonstrate that SCAIR substantially improves performance over existing KG-RAG methods. Crucially, our study highlights that reliable enterprise graph reasoning cannot rely on generic agentic designs; instead, it must explicitly incorporate the target domain's structural and operational constraints into the reasoning process. We demonstrate that by aligning agent design with business logic, substantial performance gains can be achieved without the need for costly model retraining.

SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs

Pricing automation in large-scale tourism is challenging due to informal orders and rapidly evolving, open-ended policies. Rule engines are brittle, while unconstrained LLM agents lack the reliability and auditability required for financial decisions. We present a production LLM-powered pricing system with a strict decision boundary: LLMs perform structured extraction and bounded policy/path selection, while all numeric pricing (including total-price computation) is executed deterministically. Policies are compiled into interpretable condition trees, exposing auditable artifacts and supporting human-in-the-loop control; tree induction and path matching are improved via periodic fine-tuning on logged traces. Deployed at a municipal state-owned tourism enterprise across 7 scenic sites and 12 business categories with 1,500+ operators, the system processed 3,960 orders in six months, reduced the order management team from 15–20 to 3, and cut per-order handling time from ∼10 minutes to < 2 minutes.

Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework

The matching paradigm is fundamental to large-scale information retrieval and is widely used in industrial search and advertising systems. Existing approaches employ Large Language Models (LLMs) primarily as feature extractors, underutilizing their full modeling capabilities. To address this limitation, we propose a novel matching paradigm, termed the Unified Generative and Discriminative LLM (UGD). It integrates two-tower, single-tower, and generative tasks within a unified LLM framework via attention-mask partitioning, enabling generative tasks to serve as auxiliary supervision for discriminative learning and facilitating distillation from single-tower to two-tower architectures through a multi-task fine-tuning mechanism. To satisfy online latency constraints, we further introduce a self-distillation variant of UGD with a KMeans-enhanced linearized RQVAE for prompt compression and quantization. This design compresses and quantizes landing-page documents during inference, improving serving efficiency and reducing storage overhead. Extensive experiments show that UGD achieves superior performance and strong practical value. The framework has been deployed in an industrial search engine serving hundreds of millions of users and hundreds of thousands of advertisers, significantly enhancing search experience. Open access upon publication.

A Novel Matching Paradigm: Unified Generative and Discriminative LLM with Prompt Compression for Relevance Learning

Jurisdictionally bound domains, such as law, often lack standardized, machine-readable data formats, requiring foundational infrastructure before downstream applications can succeed. We present ThLexGraph, the first unified temporal knowledge graph for Thai legal data, integrating 3,840 laws (6,273 versions) with 87,394 Supreme Court decisions, updated daily. The graph encodes hierarchy, temporal versioning, cross-references, and sequential order, all extracted from unstructured official sources where no structured representation previously existed. A five-setting comparison on NitiBench-Tax isolates data infrastructure as the sole variable: graph-structured retrieval achieves Citation F1 of 0.812 versus 0.666 for practitioner-standard web search and 0.685 for flat vector retrieval, while searching a corpus 53x larger. Trace analysis of 820 agent-issued queries reveals that hierarchy traversal and cross-reference following, capabilities absent from generic retrieval, are exercised in 50% and 16% of questions, respectively. Our system demonstrates that structured modeling of hierarchy, temporal versioning, cross-references, and sequential order can overcome structural limitations of legal data published without standardized formats.

ThLexGraph: A Production Knowledge Graph Unifying Thailand’s Legal System

Building monolingual language models (LMs) for low-resource languages typically relies on adapting pretrained language models (PLMs) by finetuning the whole model on the target language. This approach is widely favored over training from scratch, as it enables effective knowledge transfer. Additionally, prior work has shown that using a language-specific tokenizer can enhance the adaptability. In this work, we hypothesize that full model tuning is often unnecessary and propose a more modular approach. Specifically, we replace the tokens, freeze the corresponding embeddings, and tune the rest of the model. We use Scottish Gaelic, Irish, and Quechua for our experiments, with Quechua being a very low-resource language (8.5k training instances). Evaluation on natural language understanding (NLU) tasks -- mask-filling, NER, and POS -- shows that our proposed approach improves performance when adapting the models to low-resource languages. Additionally, we provide a comprehensive analysis of the effectiveness of training strategies, the choice of pretrained embeddings, and models.

Modular Monolingual Adaptation using Pretrained Language Models

While large-scale generative speech models have achieved remarkable semantic coherence, industrial deployment remains constrained by a fidelity ceiling typically capped at lower sampling rates. A fundamental limitation is the reliance on intermediate mel-spectrograms, a low-dimensional bottleneck that discards phase and high-frequency information, causing artifacts in expressive scenarios like singing. In this work, we introduce ResoDiff-44k, a production-grade generative foundation model designed for cinema-quality, 44.1kHz audio synthesis. Departing from standard masked audio modeling and mel-spectrogram inversion, ResoDiff-44k leverages Discrete Diffusion over a pure Descript Audio Codec latent space. We pre-train ResoDiff-44k on a massive 150K -hour multilingual dataset to establish a robust acoustic prior, followed by targeted fine-tuning on a curated regional mixed-language and singing corpus. Our experiments demonstrate that replacing the standard prediction head with a discrete diffusion trajectory significantly reduces misalignment in long sequences. We report a double-blind subjective evaluation showing that ResoDiff-44k achieves a 4.6 Mean Opinion Score in 44.1kHz singing synthesis and a 71\% reduction in character error rate on regional mixed-language prompts compared to strong baselines. The proposed pipeline offers a viable path for deploying high-fidelity, culturally adaptive conversational agents.

ResoDiff-44k: High-Fidelity Cross-Lingual Speech and Singing Synthesis via Discrete Diffusion

Multi-tenant enterprise search platforms serve hundreds of customers through a single shared retrieval model. Fine-tuning on individual customer data is typically prohibited by contractual and regulatory constraints, and maintaining per-customer models does not scale. We present index-time prefix injection, a training-free method that improves retrieval relevance by prepending domain-descriptive natural-language prefixes to documents during indexing. For example, prepending "IT service management knowledge article:" to an IT knowledge base shifts its embeddings into a tighter, more domain-coherent region of the vector space. Prefixes are discovered through a tiered strategy: LLM-based generation from document samples when data policies allow, domain-expert curation when they do not, and a standardized prefix library as fallback. Deployed across 18 languages and 400+ customer instances, the approach yields 3–8% Hit@5 improvements with zero model training. A/B tests confirm a 4.2% CTR lift. We describe the system design, evaluation at scale, and deployment lessons including failure modes.

Index-Time Prefix Injection for Multi-Tenant Retrieval: Improving Search Relevance Without Model Fine-Tuning

Automatic prompt optimization (APO) has emerged as a powerful paradigm for improving LLM performance without manual prompt engineering. Reflective APO methods such as GEPA iteratively refine prompts by diagnosing failure cases, but the optimization process remains black-box and label-free, leading to uninterpretable trajectories and systematic failure. We identify and empirically demonstrate four limitations: on GSM8K with a defective seed, GEPA degrades accuracy from 23.81\% to 13.50\%. We propose VISTA, a multi-agent APO framework that decouples hypothesis generation from prompt rewriting, enabling semantically labeled hypotheses, parallel minibatch verification, and interpretable optimization trace. A two-layer explore-exploit mechanism combining random restart and epsilon-greedy sampling further escapes local optima. VISTA recovers accuracy to 87.57\% on the same defective seed and consistently outperforms baselines across all conditions on GSM8K and AIME2025.

Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization

Understanding idiomatic and figurative language in images remains a fundamental challenge for vision–language models, as it requires reasoning beyond literal image–text alignment. Although large pretrained models such as CLIP and BLIP-2 perform well on literal recognition, they consistently fail on multimodal figurative benchmarks, often favoring visually salient but semantically literal interpretations. We show that this failure arises from a systematic literal alignment bias rather than limited model capacity. Motivated by this observation, we reformulate multimodal figurative understanding as a contrastive semantic deviation problem, where figurative images must be distinguished from visually plausible literal alternatives. We introduce a parameter-efficient adaptation of CLIP using Low-Rank Adaptation (LoRA) with hard literal negative mining, achieving targeted reshaping of multimodal representations without full fine-tuning. Experiments on the IRFL benchmark across idioms, metaphors, and similes demonstrate substantial improvements over zero-shot CLIP, BLIP- 2, ensemble-based, and knowledge-augmented baselines. Finally, we introduce FIGMENT, a multilingual figurative grounding evaluation spanning five idiom-rich languages, and show that the adapted model generalizes across languages despite being trained exclusively on English supervision.

Semantic Contrastive Adaptation for Multimodal Figurative Language Understanding

Chain-of-Thought (CoT) prompting is the dominant strategy for eliciting step-by-step reasoning in LLMs, yet its effect on model behavior remains poorly understood. We present a controlled study of when reasoning augmentation helps versus hurts in code generation — a task requiring deductive reasoning under formal constraints — spanning three architectures: a 2×2 design with Qwen2.5-Coder-1.5B and DeepSeek-Coder-1.3B (base and instruction-tuned variants) on HumanEval, MBPP, and LiveCodeBench, plus CodeLlama-7B. Our key finding is that instruction tuning reverses CoT's effect on the same base architecture: CoT significantly improves Qwen base (+13.4%, $p<0.001$) but significantly degrades Qwen instruct ($-15.2\%$, $p<0.001$). DeepSeek remains insensitive regardless of training regime (all $p>0.2$). To explain why, we apply layer-wise linear probing and find that all models encode prompt type (Direct vs. CoT) by Layer 1–4 ($>$90% accuracy) — universally, whether CoT helps or hurts. This reveals a key mechanistic insight: representation does not determine interpretation. The same internal signal for "this is a reasoning prompt" drives opposite behavioral outcomes depending on training regime. Building on this, we develop a probe-guided style router that selects from 12 prompt styles per problem via a single forward pass (84ms). The router is statistically indistinguishable from the best fixed style in 7/8 settings (McNemar's, all $p_{\text{Best}}>0.1$) and significantly outperforms CoT where CoT is most harmful ($p=0.012$, $h=+0.40$). Our findings argue for model-aware prompt strategies informed by internal representations rather than one-size-fits-all reasoning augmentation.

Downloads

Next from ACL 2026

SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs

Similar lecture

PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy