United States

Modern e-commerce assistants must go beyond simple product search to support inspiration, comparison, and tool-grounded fact-checking across non-linear shopping journeys. However, distilling these complex behaviors into efficient, deployable models is bottle-necked by a lack of post-training data: trajectories must cover diverse agentic workflows with high fidelity, yet the desired outputs are open-ended without a single ground truth. We propose a closed-loop Multi-Agent Simulation Framework to synthesize diverse, faithful, and policy-aligned shopping trajectories. The system orchestrates a journey-aware, stateful user simulator to drive exploration, a shopping agent that manages both tools and UI elements, and a critic agent that provides rubric-driven feedback to iteratively refine the data. On a domain-specific benchmark, this synthetic data enables a small model to significantly outperform same-size baselines and surpass a large-model baseline, achieving near-zero tool-calling errors with 8$\times$ higher inference throughput.

ACL 2026

Small Agents, Big Gains: Journey-Aware and Critic-Guided Simulation for Long-Horizon Shopping Dialogues

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.

poster

Large language models (LLMs) excel at structured information generation but face cost and latency challenges when deployed at scale in user-facing products. We present a parameter-efficient supervised fine-tuning pipeline for adapting a small language model (SLM) to structured attribute generation in e-commerce product listing, enabling continuous model improvement with implicit user feedback without expensive manual annotation. Our approach involves completeness-deficit guided curation, which ranks samples by divergence between model predictions and seller-submitted attributes, selecting the highest completeness gap examples for progressive fine-tuning. Our system is deployed on a large-scale product listing service, reducing inference costs by 98% and p90 latency by 70% using a fine-tuned SLM relative to the baseline LLM while preserving an 86.4% user acceptance rate, translating to significant monthly infrastructure savings.

Progressive Fine-Tuning for Cost-Effective Structured Attribute Generation in E-commerce

Accurate Point of Interest (POI) attribute acquisition is essential for location-based services, yet traditional modular IVR systems suffer from error accumulation and high maintenance overhead. We present DuIVRS-2, an LLM-based end-to-end framework designed for large-scale POI verification at Baidu Maps. To address the long-tail distribution of real-world interactions, our methodology first employs an FSM-guided data augmentation strategy to synthesize a balanced and diverse training dataset. We then streamline dialogue management via a selective generation scheme combined with a Chain-of-Thought (CoT) mechanism, which ensures output stability and effectively eliminates hallucinations in industrial settings. To facilitate continuous policy refinement with minimal manual effort, we design a cooperative iterative learning framework that leverages a dual-evaluator voting system. Deployed in production for two months, DuIVRS-2 processed 0.4 million calls daily and achieved a 83.9\% Task Success Rate, outperforming its predecessor by 4 percentage points while maintaining a low reaction time of 130ms. This work provides a production-proven reference for developing robust, cost-effective LLM agents for large-scale industrial dialogue applications.

DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition

LLM-as-a-Judge systems are increasingly used to evaluate text at scale, yet production deployment demands low latency, minimal cost, and compatibility with closed-source APIs. Current approaches fall short in different ways; some require many LLM calls and per-dataset prompt tuning, others depend on logit access unavailable in commercial APIs, and yet others demand multiple rounds of LLM interaction for iterative feature discovery. We present \textbf{SAJA} (\textbf{S}imple \textbf{A}pproach to \textbf{J}udge \textbf{A}lignment), built on the principle that task-specific alignment should reside in a lightweight calibration head, not in elaborate prompts or model internals. SAJA makes exactly one LLM call per item using a fixed structured rubric prompt, extracts a multi-dimensional feature vector, and maps it to a human-aligned score via a calibration head trained on a small number of human labels. No prompt optimization, no logit access, and no iterative LLM interaction are needed, yet SAJA matches far more complex systems across four evaluation paradigms, achieving 86\% F1 on MT-Bench pairwise preference (vs.\ 78\% uncalibrated), competitive performance on five classification benchmarks with a single call, and +5.71\% F1 over prompt-optimized baselines on proprietary data. Ablations confirm that multi-dimensional rubric features outperform one-dimensional calibration (SummEval $\rho$ improves from $0.60$ to $0.74$) and that coarse rubric outputs recover the same human alignment as full logit distributions ($\rho = 0.36$ vs.\ $0.37$), establishing that logit access is unnecessary for calibrated judge alignment.

SAJA: A Simple Approach to Judge Alignment for LLM-as-a-Judge

Clinical decisions are often required under incomplete information. Clinical experts must identify whether available information is sufficient for judgment, as both premature conclusion and unnecessary abstention can compromise patient safety. To evaluate this capability of large language models (LLMs), we developed ClinDet-Bench, a benchmark based on clinical scoring systems that decomposes incomplete-information scenarios into determinable and undeterminable conditions. Identifying determinability requires considering all hypotheses about missing information, including unlikely ones, and verifying whether the conclusion holds across them. We find that recent LLMs fail to identify determinability under incomplete information, producing both premature judgments and excessive abstention, even when they correctly explain the underlying scoring knowledge and perform well under complete information, as they tend to assume plausible values for missing information. These findings suggest that existing benchmarks are insufficient to evaluate the safety of LLMs in clinical settings. ClinDet-Bench provides a framework for evaluating determinability recognition, leading to appropriate abstention, with potential applicability to medicine and other high-stakes domains, and is publicly available.

ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making

Industrial maintenance platforms contain rich but fragmented evidence, including free-text work orders, heterogeneous operational sensors or indicators, and structured failure knowledge. These sources are often analyzed in isolation, producing alerts or forecasts that do not support conditional decision-making: given this asset history and behavior, what is happening and what action is warranted?


We present Condition Insight Agent, a deployed decision-support framework that integrates maintenance language, behavioral abstractions of operational data, and engineering failure semantics to produce evidence-grounded explanations and advisory actions. The system constrains reasoning through deterministic evidence construction and structured failure knowledge, and applies a rule-based verification loop to suppress unsupported conclusions.


Case studies from production CMMS deployments show that this verification-first design operates reliably under heterogeneous and incomplete data while preserving human oversight. Our results demonstrate how constrained LLM-based reasoning can function as a governed decision-support layer for industrial maintenance.

Evidence‑Driven Reasoning for Industrial Maintenance Using Heterogeneous Data

The Model Context Protocol (MCP) has rapidly emerged as the dominant standard for connecting large language models to external tools, databases, and services. Yet this convenience introduces a fundamentally new attack surface that existing LLM safety measures fail to address: adversaries can now compromise AI agents not through the user prompt, but through the tools the agent trusts. We present ShieldMCP, a runtime security framework grounded in two contributions. First, we introduce a structured threat taxonomy derived from analysis of 80+ attack techniques catalogued under the SAFE-MCP initiative within the Linux Foundation's OpenSSF, spanning 14 tactical categories adapted from the MITRE ATT&CK methodology. Second, we describe an interception architecture that performs real-time validation of MCP tool calls and responses, combining structural analysis with semantic intent verification to detect tool poisoning, indirect prompt injection through tool outputs, and supply chain manipulation. In red-team evaluation across five popular LLM backends, ShieldMCP reduces attack success rates from 74% to under 9% for tool poisoning and from 47% to under 6% for indirect prompt injection via tool responses, while adding fewer than 120ms of median latency per tool call. We discuss deployment considerations, the tension between security and agent utility, and lessons applicable to any organization integrating MCP into production workflows. Our framework is categorized as an Emerging system intended for real-world deployment.

Securing the Tool Layer: A Threat Taxonomy and Runtime Defense Framework for Model Context Protocol Deployments

Modern data lakes contain vast and heterogeneous document collections, making Information Extraction (IE) a persistent and nontrivial challenge. Traditional IE systems are often rigid - i.e. domain-specific, require extensive supervision, or are limited to predefined entity types and data structures; LLM-based approaches are more flexible, but suffer from hallucinations, non-determinism, high computational costs - drawbacks inherent to all LLMs. To overcome these limitations, we introduce OSyTa, a novel scalable LLM-based IE system that processes documents of varying complexity, extracts relational tables, and can generate complex tables with Bi-dimensional metadata, enabling robust document-level IE.
We evaluated OSyTa on real user extraction tasks and \textcolor{blue}{achieved high F1 score (92.1\%) across three publicly available}, large-scale corpora from two distinct domains (medical and legal) each containing numerous documents.

OSyTa: Optimizer-based System for Table Generation from Documents

Large language models (LLMs) face a fundamental trade-off between factual consistency and reasoning diversity. Deterministic decoding strategies prioritize reliability but may fail to explore alternative solution paths, while high-temperature sampling increases exploration at the cost of factual accuracy. We present FROST (Factual Reasoning via Optimized Stochastic Trajectories), an inference framework that systematically balances exploration and exploitation for cost-efficient reasoning in production environments. FROST combines deterministic inference from large models with targeted stochastic sampling from smaller models, followed by multi-criteria validation to select factually grounded outputs. The framework operates entirely at inference time, requiring no additional training or fine-tuning. Across HotpotQA, CommonsenseQA, and MMLU, FROST achieves 3--5\% accuracy improvements over standard chain-of-thought prompting. Crucially, it maintains high cost-efficiency relative to other robust inference methods, achieving a 28\% cost reduction compared to Self-Consistency ensembles through strategic delegation to smaller models. Validation analysis demonstrates that FROST reduces unsupported outputs by 40\% relative to baseline methods. Task-stratified evaluation reveals that exploration benefits scale with problem ambiguity, with alternative reasoning paths improving accuracy in 23--34\% of multi-hop questions. These results establish FROST as a practical approach for deploying reliable and efficient reasoning systems in production environments.

FROST: Factual Reasoning via Optimized Stochastic Trajectories in Large Language Models during Inference

Extracting structured data from unstructured text using large language models (LLMs) becomes challenging when the target schemas are large and complex. In such cases, including the full schema in the prompt increases cost and latency, risks lost-in-the-middle performance degradation, and can exceed context length limits. We propose SchemaRAG, a retrieval-augmented generation (RAG) framework that dynamically prunes the output schema space for schema-conditioned information extraction tasks by leveraging schema metadata and few-shot examples (when available). We evaluate SchemaRAG on real-world healthcare and e-commerce datasets. Our results show that SchemaRAG can achieve up to an 8.8% increase in micro-F1, a 47% reduction in latency, and a 48% reduction in token costs, demonstrating its practicality for large-schema extraction.

SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction

Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user reports to identify an underlying root cause. While retrieval-augmented generation (RAG) provides grounding through historical cases, standard multi-turn RAG systems lack explicit diagnostic state and therefore struggle to accumulate evidence and resolve competing hypotheses across turns.


We introduce DQA, a diagnostic question-answering framework that maintains persistent diagnostic state and aggregates retrieved cases at the level of root causes rather than individual documents. DQA combines conversational query rewriting, retrieval aggregation, and state-conditioned response generation to support systematic troubleshooting under enterprise latency and context constraints.


We evaluate DQA on 150 anonymized enterprise IT support scenarios using a replay-based protocol. Averaged over three independent runs, DQA achieves a 78.7\% success rate under a trajectory-level success criterion, compared to 41.3\% for a multi-turn RAG baseline, while reducing average turns from 8.4 to 3.9. This improvement reflects the benefit of explicitly representing competing explanations and aggregating evidence across turns in unscripted troubleshooting.

Downloads

Next from ACL 2026

Progressive Fine-Tuning for Cost-Effective Structured Attribute Generation in E-commerce

Similar lecture

ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES