United States

The rapid growth of scientific publications makes it increasingly difficult to track and synthesize research progress. While Large Language Models (LLMs) can support automated survey generation, existing methods retrieve unstructured data and require models to infer conceptual, methodological, and taxonomic relations from raw text at generation time. We introduce StructSurvey, a hierarchical multi-agent framework that shifts structural reasoning from generation to retrieval by dynamically constructing graph-based representations of entities, relations, and topical taxonomies. We evaluate StructSurvey on a new reference-grounded benchmark of ACL survey papers for reproducible long-form scientific summarization. Compared with embedding-only retrieval baselines, StructSurvey improves ROUGE-1 recall by +2.9 and ROUGE-2 recall by +1.0 on average, without reducing precision. It also improves LLM-as-a-Judge ratings for logical structure, depth, and synthesis, showing that explicit structural retrieval yields surveys closer to human-written organization and reasoning.

ACL 2026

StructSurvey: Structured Agentic Retrieval for Automatic Survey Paper Generation

reference-grounded evaluation

long-form scientific summarization

entity-relation extraction

topical taxonomies

hierarchical multi-agent systems

graph-based representations

scientific survey generation

structured retrieval

llm-as-a-judge

retrieval-augmented generation

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

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.

workshop paper

Retrieval-Augmented Generation (RAG) represents a significant advancement in artificial intelligence combining a retrieval phase with a generative phase, with the latter typically being powered by Large Language Models (LLMs). Common wisdom and practices in RAG involve using "instructed" LLMs, which are fine-tuned with supervised training to enhance their ability to follow instructions and are aligned with human preferences using state-of-the-art techniques. However, contrary to this popular belief, our study demonstrates that base models outperform their instructed counterparts in RAG tasks by 20\% on average under our experimental settings. This finding challenges the prevailing assumptions about the superiority of instructed LLMs in RAG applications. Further investigations reveal a more complex situation, questioning fundamental aspects of RAG and suggesting the need for broader discussions on the topic; or, as Fromm would have it, "Seldom is a glance at the statistics enough to understand the meaning of the figures".

A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems

Retrieval-Augmented Generation (RAG) grounds language-model output in external knowledge, yet its application to dense technical documentation remains largely unexplored. Engineering software manuals pose compounding challenges: formulae are corrupted during PDF extraction, heterogeneous content types require different parsing treatment, and queries demand cross-document synthesis across multiple reference volumes. We present an end-to-end RAG system for OpenFOAM, an open-source computational fluid dynamics toolkit, operating in two modes. In single-query mode, a formula-preserving parser (Marker), adaptive header-aware chunking, two-stage dense-then-rerank retrieval, and a citation-enforcement prompt produce grounded, source-attributed answers across a 20-question benchmark. In report mode, a user prompt is decomposed into sub-questions via LLM planning; each sub-question undergoes independent retrieval and cross-encoder re-ranking, and the deduplicated chunk set is passed to a long-context generation call that produces a structured, multi-section report with inline citations. Evaluated on a 10-prompt golden set with a six-dimension LLM-as-a-judge framework, both pipelines achieve overall scores above 4.6/5.0 with perfect citation correctness (5.0/5.0). The decomposed pipeline demonstrates superior robustness (90% vs 70% judge success rate). Retrieval analysis using page-level ground truth reveals low absolute recall (<14%), identifying retrieval breadth as the primary bottleneck.

Decompose, Retrieve, Cite: A RAG Pipeline for Structured Report Generation from Technical Documentation

We introduce $\textbf{EncouRAGe}$, a comprehensive Python library designed to streamline the development and evaluation of Retrieval-Augmented Generation (RAG) systems using Large Language Models (LLMs) and Embedding Models. EncouRAGe comprises five modular and extensible components: $\textit{Type Manifest}$, $\textit{RAG Factory}$, $\textit{Inference}$, $\textit{Vector Store}$, and $\textit{Metrics}$, facilitating flexible experimentation and extensible development. Each component helps to make development RAG evaluation and emphasizes $\textbf{scientific reproducibility}$, $\textbf{diverse evaluation metrics}$, and $\textbf{local deployment}$, enabling researchers to efficiently assess datasets within RAG workflows. This paper presents implementation details and an extensive evaluation across multiple benchmark datasets, including $\textit{25k QA pairs}$ and $\textit{over 51k documents}$. Our results show that RAG still underperforms compared to the $\textit{Oracle Context}$, while $\textit{Hybrid BM25}$ consistently achieves the best results across all four datasets. $\textbf{Code}$: https://github.com/uhh-hcds/encourage

EncouRAGe: Evaluating RAG Local, Reliable and Efficient

Operational safety in mission-critical environments requires AI systems that are accurate, interpretable, and resistant to hallucination. We present an agentic Retrieval-Augmented Generation (RAG) framework, REFSafe, for grounded hazard analysis and automated safety report generation. The system integrates Large Language Models (LLMs) with structured operational data, historical incident repositories, policy documents, and external authoritative sources. Through iterative agentic reasoning, the framework retrieves, verifies, and synthesizes evidence prior to generation, enforcing citation-backed outputs with explicit source attribution (documents, links, and prior events) to ensure traceability and trust. To mitigate hallucinations and unsupported claims, all risk assessments and forecasts are constrained to retrieved evidence, with confidence signals derived from retrieval relevance and source consistency. A transparent pipeline enables subject matter experts (SMEs) to validate predictions, and provide structured feedback, forming a continuous performance calibration loop. Preliminary deployment demonstrates improved reliability in hazard detection and safety/vulnerability report generation. This work advances trustworthy, evidence-grounded AI for predictive safety intelligence in mission-critical operations.

REFSafE: A RAG-Enabled Framework for Predictive Risk Analysis and Automated Safety Report Generation in Mission-Critical Environments

High-Risk Property (HRP) classification is critical at U.S. Department of Energy (DOE) sites, where inventories include sensitive and often dual-use equipment. Compliance must track evolving rules designated by various export control policies to make transparent and auditable decisions. Traditional expert-only workflows are time-consuming, backlog-prone, and struggle to keep pace with shifting regulatory boundaries. We propose ORCHID, a modular agentic framework for HRP classification that pairs retrieval-augmented generation (RAG) with human oversight to produce policy based outputs that can be audited. Small cooperating agents‚Äîretrieval, description refiner, classifier, validator, and feedback logger‚Äîcoordinate via agent-to-agent messaging and invoke tools through the Model Context Protocol (MCP) for model-agnostic on-premise operation. The interface follows an "Item to Evidence to Decision" loop with step-by-step reasoning, on-policy citations, and append-only audit bundles (run-cards, prompts, evidence). In preliminary tests on real HRP cases, ORCHID improves accuracy and traceability over a non-agentic baseline while deferring uncertain items to Subject Matter Experts (SMEs). The demonstration shows single item submission, grounded citations, SME feedback capture, and exportable audit artifacts‚Äîillustrating a practical path to trustworthy LLM assistance in sensitive DOE compliance workflows.

ORCHID: Orchestrated Retrieval-Augmented Classification of High-Risk Property with Intelligent Decision-Making

Automating systematic reviews (SRs), i.e., evidence-driven analyses under explicit protocol constraints, is a natural target for retrieval-augmented generation and deep research agents, yet existing benchmarks evaluate isolated subtasks or assume fixed evidence inputs. We introduce RAG4SR-CS-200, a benchmark of 200 computer science systematic reviews designed for protocol-driven systematic review automation. Each instance comprises review objectives, research questions, eligibility criteria, cleaned full-text review structure, references, and extracted tables. These elements support evaluation across key tasks in systematic review creation such as literature retrieval, eligibility screening, citation-grounded review generation, and structured table generation, in both stage-wise and end-to-end settings. RAG4SR-CS-200 provides a foundation for developing more reliable and diagnosable deep research agents for scientific evidence synthesis. Code and data are publicly available (https://github.com/webis-de/rag4sr-cs-200).

A Pipeline to Bootstrap the Evaluation of Retrieval-Augmented Generation for the Automation of Systematic Reviews in Computer Science

We enter both tracks of the RAG4Reports challenge with two complementary components built on a shared idea: open-ended question nuggets. PrefNugget derives concise nugget banks from pairwise preferences between system responses. PrefNugget, and its ungrounded ablation RUBRIC, are used to predict the leaderboard of RAG systems. 
Crucible is a RAG system which uses such nugget banks to generate reports with citations. For each nugget, it will extract relevant text spans, which can be taken as-is (extract) or polished with generation.

Crucible@Rag4Reports: Using Nuggets for Evaluation and RAG

This system paper presents AMU's submission to RAG4Reports 2026 Task B: a practical multilingual retrieval-augmented generation pipeline for evidence-supported report generation. The system combines full-query retrieval, optional query rewriting, dense retrieval with Qdrant, cross-encoder reranking, diversity-aware context selection, and structured generation. The best submitted run uses BAAI/bge-m3 embeddings, BAAI/bge-reranker-v2-m3 reranking, and gpt-5.1 generation with medium reasoning effort, using a partial-coverage prompt strategy. On the official leaderboard, it achieved F1=0.4351, sentence_support=0.8280, and nugget_coverage=0.3403, indicating that the generated reports were well grounded but only partially comprehensive.

AMU at RAG4Reports 2026 Task B: A Practical Multilingual RAG Pipeline for Citation-Grounded Reports

Reliable automatic evaluation of retrieval-grounded long-form reports typically requires human annotation or frontier-scale proprietary LLMs, both of which are expensive in constrained settings. Team rgipt participated in RAG4Reports@ACL 2026 Task 1 with a zero-shot nugget-verification system that runs entirely on a single NVIDIA T4 GPU. We compare three ultra-lightweight decoder-only models: Qwen2-0.5B, Qwen2-1.5B, and Qwen2.5-0.5B, under identical inference conditions to examine how small an LLM judge can be while retaining human-aligned ranking signal. Both Qwen2 models produced negative $\tau_{\text{gap}}$, whereas Qwen2.5-0.5B achieved $\tau_{\text{gap}} = 0.0772$ and Pearson $r = 0.2209$, ranking 13th of 21 teams. Within this family and evaluation setting, model generation appears to matter more than parameter count, although this finding is based on three configurations on a single task and warrants further validation.

Exploring Capability Thresholds in Ultra-Lightweight LLM Judges for Nugget-Based Report Evaluation

We describe EFSG (Evidence-First Structured Generation), our submission to Task B of the RAG4Reports@ACL 2026 shared task. Standard retrieval-augmented generation pipelines allow generation models to write from parametric memory and attach citations retroactively: a behaviour we term post-rationalization. EFSG addresses this structurally through a phase boundary: all evidence is retrieved, extracted, and sealed into a fact pool before any generation begins; each sentence then sees only its single committed source passage. Our best run (t5100k doc corpus) achieved sentence_support of 0.612 and nugget_coverage of 0.126 (F1 = 0.182).

Downloads

Next from ACL 2026

A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems

Similar lecture

StructSurvey: Structured Agentic Retrieval for Automated Survey Paper Generation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL 2026

A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems

Similar lecture

StructSurvey: Structured Agentic Retrieval for Automated Survey Paper Generation

Downloads