United States

We argue that LLM-based coding agents frequently fail to solve problems that lie within the model&#39;s capacity and the bottleneck is often the conditioning context rather than the model itself. We formalize this for the full class of Turing-computable problems with verifiable specifications and introduce a framework that recasts coding as optimization over a latent space of intentions—natural-language descriptions of high-level solution strategies—and searches this vector space with feedback guidance to steer coding agent toward correct solutions of the problems. The method operates as a plug-in layer that can wrap any coding agent without modifying its architecture or weights. On SWE-Bench Verified, our method raises the resolution rate of a weak, quantized 24B open-weight model to parity with frontier models +25× its size.

ACL 2026

Beyond Discrete Search: Divergent Thinking as Optimization in Latent Intention Space

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

We argue that LLM-based coding agents frequently fail to solve problems that lie within the model's capacity and the bottleneck is often the conditioning context rather than the model itself. We formalize this for the full class of Turing-computable problems with verifiable specifications and introduce a framework that recasts coding as optimization over a latent space of intentions—natural-language descriptions of high-level solution strategies—and searches this vector space with feedback guidance to steer coding agent toward correct solutions of the problems. The method operates as a plug-in layer that can wrap any coding agent without modifying its architecture or weights. On SWE-Bench Verified, our method raises the resolution rate of a weak, quantized 24B open-weight model to parity with frontier models +25× its size.

poster

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.

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.

Negotiation involves complex emotional and strategic dynamics that pose challenges for AI agents in negotiation dialogues. This paper proposes a zero-shot soft-labeling method using an large language model-based embedding model and verifies its performance on negotiation dialogues. Furthermore, it examines the performance of predictive model training on rule-based annotated hard and soft labels obtained by the proposed method for the task of predicting whether agreement will be reached from partial dialogues, namely, final disagreement anticipation in negotiation mid-dialogues (FDANMD). Soft labeling obtained by the proposed method showed a maximum HIT@3 score of 0.87 against rule-based annotated hard labels, whereas failure cases also demonstrated the limitations of rule-based annotation. Furthermore, using ROC AUC, evaluations of FDANMD across three datasets (CB, DN, and JI) with negotiation progress rates of 0.25, 0.5, and 1.0 revealed that soft labeling is particularly effective at low negotiation progress rates and also offers superior performance on individual datasets and unseen datasets for models trained on multiple datasets. These results motivate the use of soft labeling to incorporate the complexity of negotiation dialogues into intermediate representations and support the generalizability of zero-shot soft labeling and generalizable predictors across a wide range of negotiations beyond known domains.

LLM-Based Zero-Shot Soft Labeling for Anticipating Disagreement in Negotiation Dialogues

We investigate the extent to which the language processing of LLMs resembles human cognitive processes, focusing on a human cognitive bias called the *neglect-zero effect*. This effect refers to the human tendency to ignore *zero-models*, which are configurations that render a proposition vacuously true by virtue of an empty set. We focus on two types of inference driven by the neglect-zero effect, and examine how LLMs process the inference by comparing their behavior with that in inference not involving the neglect-zero effect. For this purpose, we employ a paradigm using *structural priming*, where recent exposure to a preceding sentence (the *prime*) facilitates the processing of a subsequent sentence (the *target*) due to their structural similarity. We prepare primes so that they force LLMs to consider the zero-model, and analyze whether they also consider zero-models in the target. The results indicate the possibility that the neglect-zero effect does not arise within the LLMs analyzed in this study.

Analysis of the Neglect-Zero Effect in Large Language Models

Constrained decoding systems are often built on context-free parsers intended for programming languages. These parsers either degrade into $O(n^3)$ time-complexity or fail entirely if the grammar is not carefully engineered to keep properties such as determinism and non-ambiguity. There is thus a need to design parsers that efficiently handle non-determinism and ambiguity, while simultaneously being incremental so that they can be coupled with the token-based predictions of large language models. Inspired by prior work, we derive an incremental CYK prefix recognizer, which still has $O(n^3)$ complexity but allows for acceleration with only a fraction of GPU resources (stream multiprocessors). Our parser shows robust efficiency in complex context-free grammars while other parsers crash or degrade. At the same time, we remain empirically competitive in restrictive grammar classes such as LALR.

An Incremental CYK Recognizer for GPU-accelerated General Context-free Prefix Validation

The text-to-table task aims to generate structured data in tabular formats from unstructured text. While the integration of large language models (LLMs) has significantly enhanced the comprehensiveness and flexibility of generation, challenges regarding inconsistent output quality persist, such as the inclusion of redundant information and numerical inaccuracies. We propose TableMBR, a robust table generation method that maintains structural consistency through minimum Bayes risk (MBR) decoding. Experimental results showed that TableMBR outperforms the baseline, achieving relative improvements of up to 15% in F1 score on Rotowire and 23% in accuracy on LiveSum.

TableMBR: Minimum Bayes Risk Table Generation Based on Structural Consistency

Large language models (LLMs) are increasingly used as evaluative tools across languages, yet bias research remains overwhelmingly Anglocentric, with most studies conducted in English using Latin-script names. It remains unclear whether bias patterns generalize across linguistic contexts. We investigate this question and introduce the stereotype perceptual map, a framework for analyzing how ethnic groups are positioned along evaluative dimensions. Using 900,000 model responses over 45,000 names spanning 9 ethnicities, we evaluate model behavior across prompt languages (English, Chinese, Thai), writing scripts (Latin, Chinese, Thai), evaluative domains (competence, warmth), and models (GPT, DeepSeek). We find that ethnic bias hierarchies are jointly shaped by local linguistic context and model origin and differ substantially between Western-centric and Sinocentric models. DeepSeek exhibits highly stable rankings across conditions in math competence judgments, consistently placing Chinese at the top, followed by Russian, and White, Hispanic, and Black names at the bottom. GPT, by contrast, shows strong script-dependent reordering: Latin-script conditions form one stable cluster, while native-script conditions form another, with substantially lower cross-cluster correlations. We term this script-gated bias: transliterating the same names into a non-Latin script can activate a different evaluative frame and produce rankings that are sometimes inversely correlated with Latin-script results. Warmth evaluations are less stable than competence across both models. Our findings demonstrate that multilingual bias cannot be characterized through single-language, single-script audits. For multilingual users, code-switching between languages can toggle between different bias regimes. Fairness evaluations for multilingual LLMs must therefore account for deployment language, writing system, and model origin to capture the full range of potentially harmful bias these systems exhibit.

Through the Looking Glass of Multilingual AI: Contrasting Language- and Name Script-Dependent Ethnic Hierarchies in GPT and DeepSeek

We propose a comprehensive research agenda to detect, measure, and mitigate racial bias in Natural Language Processing (NLP) systems deployed in criminal justice contexts. Our preliminary work demonstrates that racial descriptors systematically alter embedding similarity scores and retrieval rankings across six models, with bias being race-specific and models showing rank displacements of 1.82 to 7.44 positions, on average. This empirically indicates that even small shifts in similarity scores can displace relevant records outside top-10 results, leading to systematic under-retrieval of records involving certain demographic groups. Building on these findings, this thesis proposes four research questions: (1) developing and evaluating debiasing techniques including counterfactual data augmentation, adversarial training, and fairness-constrained fine-tuning; (2) validating synthetic findings on authentic law enforcement data through IRB-approved partnerships; (3) investigating intersectional bias patterns across race, gender, and age; and (4) we extend beyond embedding-level analysis to examine how bias propagates across modern multi-stage retrieval pipelines from embeddings to cross-encoders to LLMs. Expected contributions include empirical comparisons of debiasing methods, bias benchmarks for criminal justice NLP, deployment guidelines for fairness-aware retrieval systems, and the first comprehensive analysis of multi-stage bias propagation in retrieval pipelines.

Thesis Proposal: Auditing and Mitigating Demographic Bias in Multi-Stage Retrieval Systems for Criminal Justice Applications

Scenario-based text generation has broad applications across education and creative writing, but remains underexplored in controllable text generation. We introduce the Contextual Diversity Measure (CDM), a metric that quantifies semantic diversity for scenario generation given an abstract semantic role labeling constraints, and validate it through controlled experiments. Statistical analysis across four embedding models demonstrates that CDM successfully distinguishes between high-diversity and low-diversity text pairs, with all tests achieving significance at $p < 0.05$ on both subsets of the dataset, with effect sizes from small-to-medium (Cohen's $d$ from 0.292 to 0.508) and medium-to-large ($d$: 0.677--1.195). Baseline comparisons indicate that CDM achieves excellent discrimination accuracy (100\% and 91.9\% for the two subsets), with discriminative power up to $5.5\times$ greater than the best~baseline.

Contextual Diversity Measure (CDM) for Controllable Story Generation in Large Language Models

The development of fact-checking systems for verifying the factuality of text generated by large language models (LLMs) has been advancing. In the verdict prediction step of such systems, the system determines whether claims in the generated text are supported by retrieved evidence, formulated as a natural language inference (NLI) task. This study extends the label set for verdict prediction to capture claim-evidence relationships that humans would commonly interpret as supported or refuted, even in the absence of strict logical entailment or contradiction. It also constructs a Japanese dataset comprising 28,147 instances from two sources based on this extended label set. We analyze the causes of annotation disagreement and find that ambiguity in the boundary of acceptable inference, interpretive characteristics of negative cases, and incomplete information in the evidence affect annotation variability. Using this dataset, we evaluate the performance of prompt-based verdict prediction methods and show that prompts that explicitly elicit chain-of-thought reasoning improve F1 by 4 percentage points compared to baseline.

Constructing a Japanese Verdict Prediction Dataset for Fact-Checking of LLM-Generated Texts

We disentangle multilingual sentence embeddings into language-dependent and language-agnostic components, leveraging the latter to improve cross-lingual similarity estimation. Previous studies focused on encoder-based approaches that use only the input sentence; in contrast, this study examines the effectiveness of disentanglement methods across a broader range of sentence embeddings, including decoder-based approaches and those that utilize prompts. Experimental results demonstrate that embedding disentanglement is effective for a wide variety of sentence embeddings.

Disentangling Meaning and Language Components in Diverse Multilingual Sentence Embeddings

Vision-Language Models (VLMs) excel at multimodal tasks, but they remain vulnerable to hallucinations that are factually incorrect or ungrounded in the input image. Recent work suggests that hallucination detection using internal representations is more efficient and accurate than approaches that rely solely on model outputs. However, existing internal-representation-based methods typically rely on a single representation or detector, limiting their ability to capture diverse hallucination signals. In this paper, we propose EnsemHalDet, an ensemble-based hallucination detection framework that leverages multiple internal representations of VLMs, including attention outputs and hidden states. EnsemHalDet trains independent detectors for each representation and combines them through ensemble learning. Experimental results across multiple VQA datasets and VLMs show that EnsemHalDet consistently outperforms prior methods and single-detector models in terms of AUC. These results demonstrate that ensembling diverse internal signals significantly improves robustness in multimodal hallucination detection.

Downloads

Next from ACL 2026

LLM-Based Zero-Shot Soft Labeling for Anticipating Disagreement in Negotiation Dialogues

Similar lecture

Code Like Humans: A Multi-Agent Solution for Medical Coding

.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

LLM-Based Zero-Shot Soft Labeling for Anticipating Disagreement in Negotiation Dialogues

Similar lecture

Code Like Humans: A Multi-Agent Solution for Medical Coding

Downloads