United States

Self-consistency improves large language models by sampling multiple reasoning paths and selecting the most frequent answer, but majority vote often fails to recover correct answers that are already present among samples. In this work, we reformulate answer selection in self-consistency as a ranking problem. Instead of relying on a single uncertainty or confidence signal, we train a lightweight reranker to score candidate answers using five carefully designed features that capture answer-level frequency, semantic centrality, and reasoning-trace consistency. We instantiate this approach with a LambdaRank model and evaluate it on three datasets under a range of test-time budgets. Across datasets, the proposed method consistently achieves a better accuracy-efficiency trade-off than standard self-consistency and strong baselines, with particularly large gains on question answering benchmarks. Further analysis shows that the proposed features are individually useful and, more importantly, complementary, highlighting the value of learning to combine multiple informative signals for test-time answer selection.

ACL 2026

Boosting Self-Consistency with Ranking

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

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.

Open Information Extraction (OIE) has largely focused on extracting relational tuples from text, yet in its current form remains unsuitable for downstream systems due to the absence of standardized, semantically sound representations. This thesis argues that the field has been addressing extraction as a surface-level prediction problem, leading to outputs that are semantically incomplete and logically ambiguous, particularly in the presence of modality, negation, conditionality, quantification, and attribution. We propose a normalization-first framework that reframes OIE as a structured semantic transformation pipeline, where raw text is first converted into a lossless, canonical form of declarative, active-voice, and irreducible sentence units, and extraction is constrained to atomic unary and binary relations augmented with explicit semantic annotations. Within a Probably Approximately Correct (PAC) learning perspective, we formalize soundness, completeness, and usefulness as approximate yet verifiable guarantees over extraction quality, acknowledging the inherent undecidability of full semantic interpretation. This thesis outlines a feasible research program to develop the theoretical foundations, models, and evaluation protocols required to produce system-ready OIE representations, thereby establishing a principled and executable path toward making OIE directly usable for downstream reasoning and machine interpretability.

Thesis Proposal: A Normalization-First Framework for Sound, Complete, and Utility-Ready Open Information Extraction

LiTS is a modular Python framework for LLM reasoning via tree search. It decomposes tree search into three reusable components—Policy, Transition, and RewardModel—that plug into algorithms like MCTS and BFS. A decorator-based registry enables domain experts to extend to new domains by registering components, and algorithmic researchers to implement custom search algorithms. We demonstrate composability on MATH500 (language reasoning), Crosswords (environment planning), and MapEval (tool use), showing that components and algorithms are orthogonal: components are reusable across algorithms within each task type, and algorithms work across all components and domains. We also report a mode-collapse finding: in infinite action spaces, LLM policy diversity—not reward quality—is the bottleneck for effective tree search. A demonstration video is available at https://youtu.be/nRGX43YrR3I. The package is released under the Apache 2.0 license at https://github.com/xinzhel/lits-llm, including installation instructions and runnable examples that enable users to reproduce the demonstrated workflows.

LiTS: A Modular Framework for LLM Tree Search

Large language model (LLM) agents are increasingly applied to financial decision-making tasks that require interaction with external tools, including market data retrieval, news analysis, and trade execution. However, existing trading systems rely on fragmented and task-specific APIs, resulting in inconsistent schemas, complex integration, and limited reproducibility. We present QFinZero, a unified trading environment for LLM-based financial agents. QFinZero standardizes three core capabilities: (i) multi-frequency market and derivatives data access, (ii) structured news and event retrieval, and (iii) stateful brokerage simulation with explicit order lifecycle management. All tools adopt consistent JSON schemas and time-aligned interfaces, enabling agents to acquire information and execute trades within a coherent framework. By abstracting financial interaction into composable, agent-invokable primitives, QFinZero reduces engineering overhead and supports reproducible evaluation through comprehensive logging and deterministic replay. We argue that such a standardized trading environment is essential for scalable research on LLM-based financial agents.

QFinZero: A Unified Financial Toolchain for LLM-Based Trading Agents

We propose Fast-MIA (https://github.com/Nikkei/fast-mia), a Python library for efficiently evaluating membership inference attacks (MIA) against large language models (LLMs).
MIA has emerged as a crucial technique for auditing privacy risks and copyright infringement in LLMs. 
However, computational demands have grown substantially: recent methods rely on repeated inference, while practical auditing requires large-scale evaluation.
Progress is further hindered by existing implementations that execute methods independently, redundantly computing shared intermediate results such as log-probabilities.
To address these challenges, Fast-MIA combines two strategies: (1) high-throughput batch inference via vLLM, achieving approximately 5$\times$ speedup, and (2) a cross-method caching architecture that computes intermediate results once and shares them across methods.
The library includes representative MIA methods under a unified framework, integrates with established benchmarks, and supports flexible YAML configuration.
We release Fast-MIA under the Apache License 2.0 to support scalable and reproducible MIA research.

Fast-MIA: Efficient and Scalable Membership Inference for LLMs

Efforts over the past three decades have produced web archives containing billions of webpage snapshots and petabytes of data. The End of Term Web Archive alone contains millions of PDFs produced by the federal government. While preservation with web archives has been successful, significant challenges for access and discoverability remain. In this paper, we introduce GovScape, a public search system that supports multimodal searches across 10,015,993 federal government PDFs from the 2020 End of Term crawl (70,958,487 total PDF pages) -- to our knowledge, all renderable PDFs in the 2020 crawl that are 50 pages or under. GovScape supports four primary forms of search: in addition to providing (1) filter conditions over metadata facets including domain and crawl date and (2) exact text search against the PDF text, we provide (3) semantic text search and (4) visual search against the PDFs across individual pages, enabling users to structure queries such as “redacted documents'' or “pie charts.'' We detail GovScape's search affordances, embedding pipeline, system architecture, and open source codebase. Significantly, the total estimated compute cost for GovScape's pre-processing pipeline for 10 million PDFs was approximately $1,500, equivalent to 47,000 PDF pages per dollar spent on compute, demonstrating the potential for immediate scalability. We evaluate GovScape by (1) analyzing 1,679 search queries and (2) benchmarking vector and keyword index efficiency using these queries. GovScape can be found at https://www.govscape.net.

GovScape: A Public Multimodal Search System for 70 Million Pages of Government PDFs

Linux kernel device drivers are tightly coupled with hardware, making them difficult to execute and test without physical devices. This heavily limits automated code analysis and vulnerability discovery. While manual modeling is unscalable, Large Language Models (LLMs) offer a new approach to scale virtual device construction across the Linux driver ecosystem. In this paper, we present DevGen, an LLM-powered tool that generates QEMU-based virtual devices directly from Linux driver source code. DevGen combines static analysis to gather necessary context, guides the LLM through step-by-step prompting, and uses an automated self-correction loop driven by compilation and execution feedback. To further reduce errors, similar fixes are retrieved from a library of common modeling failures and incorporated into the repair prompt, which supports more targeted corrections in later iterations. The generated devices finally integrate with QEMU and Syzkaller, enabling driver fuzzing without physical hardware. DevGen is evaluated on 50 PCI/PCIe drivers from Linux 6.18 using three mainstream LLMs, and successfully generates usable models for 44 drivers. In these drivers, 24% of them achieve significant improvements in fuzzing coverage, and 7 previously unknown crashes are triggered with 1 CVE assigned. These results demonstrate the practical capability of LLMs to automate complex, system-level code generation tasks.

Bridging Kernel Drivers and Virtual Device Models with LLM-Powered Automation

As global cross-lingual communication intensifies, the language barrier in visually rich documents (e.g., PDFs) remains a critical bottleneck. Existing document translation pipelines suffer from a fundamental dilemma: traditional Computer-Assisted Translation (CAT) systems discard crucial layout and structural metadata, while advanced document parsers focus solely on extraction, lacking the end-to-end linguistic processing required for complex translation tasks. To bridge this gap, we introduce \textbf{BabelDOC}, a novel Intermediate Representation (IR)-based multimodal document translation framework. By explicitly decoupling visual layout from semantic content, BabelDOC maps raw PDFs into a unified IR, enabling advanced NLP interventions—such as automatic terminology extraction, cross-page contextual translation, and dictionary-constrained generation—without compromising structural integrity. The translated semantics are subsequently re-anchored and adaptively rendered into the original layout, supporting complex elements like mathematical formulas and nested tables. Featuring a highly extensible, plugin-based ecosystem compatible with state-of-the-art LLMs, BabelDOC establishes a new paradigm for lossless cross-lingual document intelligence. The open-source toolkit and its interactive downstream applications have garnered over 7.8k stars on GitHub https://github.com/funstory-ai/BabelDOC. A demonstration video is available at https://youtu.be/chwrlApH7a4.

BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation

Large language model-based (LLM-based) multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and collaboration. MAS workflows can be naturally modeled as directed computation graphs, where nodes execute agents/sub-workflows and edges encode dependencies and message passing.
However, implementing complex graph workflows in current frameworks still requires substantial manual effort, offers limited reuse, and makes it difficult to integrate heterogeneous external context sources.
To overcome these limitations, we present MASFactory, a graph-centric framework for orchestrating LLM-based MAS.
It introduces Vibe Graphing, a human-in-the-loop approach that compiles natural-language intent into an editable workflow specification and then into an executable graph.
In addition, the framework provides reusable components and pluggable context integration, as well as a visualizer for topology preview, runtime tracing, and human-in-the-loop interaction. 
We evaluate MASFactory on seven public benchmarks, validating both reproduction consistency for representative MAS methods and the effectiveness of Vibe Graphing.
Our code (https://github.com/BUPT-GAMMA/MASFactory) and video (https://youtu.be/ANynzVfY32k) are publicly available.

MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing

Academic project websites can more effectively disseminate research when they clearly present core content and enable intuitive navigation and interaction. However, current approaches such as direct Large Language Model (LLM) generation, templates, or direct HTML conversion struggle to produce layout-aware, interactive sites, and a comprehensive evaluation suite for this task has been lacking. In this paper, we introduce Paper2Web, a benchmark dataset and multi-dimensional evaluation framework for assessing academic webpage generation. It incorporates rule-based metrics like Connectivity, Completeness and human-verified LLM-as-a-Judge (covering interactivity, aesthetics, and informativeness), and PaperQuiz, which measures paper-level knowledge retention. We further present PWAgent, an autonomous pipeline that converts scientific papers into interactive and multimedia-rich academic homepages. The agent iteratively refines both content and layout through MCP tools that enhance emphasis, balance, and presentation quality. Our experiments show that PWAgent consistently outperforms end-to-end baselines like template-based webpages and arXiv/alphaXiv versions by a large margin while maintaining low cost, achieving the Pareto-front in academic webpage generation.

Paper2Web: Let’s Make Your Paper Alive!

Formal verification can provide strong mathematical guarantees about software correctness, but it typically requires developers to write detailed formal specifications (\eg, contracts and loop invariants), which is costly and error-prone. We introduce AcslAgent, an LLM-driven neuro-symbolic demonstration system that reframes specification writing as constrained structured synthesis: large language models generate candidate specifications at the granularity of proof-relevant program components, while a symbolic verifier acts as a deterministic critic that checks legality, satisfiability, and proof adequacy, rejecting or repairing candidates in an iterative loop. This design turns unconstrained text generation into constrained structured synthesis, substantially reducing hallucinations and producing proof-ready annotations. We evaluate AcslAgent on seven benchmark suites, showing strong effectiveness. We release an open-source, Dockerized system with ensemble LLM backends and inter-modular verification support for reproducible demonstration and deployment. AcslAgent are available at: https://anonymous.4open.science/r/ACSLAgent-FB4C, the full experiment result can be accessed at: https://huggingface.co/spaces/saki222/experient_result_full, and the demonstration video is available at: https://youtu.be/rwA2kyzljac.

Downloads

Next from ACL 2026

Thesis Proposal: A Normalization-First Framework for Sound, Complete, and Utility-Ready Open Information Extraction

Similar lecture

Self-Consistency of Large Language Models under Ambiguity

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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

Thesis Proposal: A Normalization-First Framework for Sound, Complete, and Utility-Ready Open Information Extraction

Similar lecture

Self-Consistency of Large Language Models under Ambiguity

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads