China

When does a large language model (LLM) know what it does not know? Uncertainty quantification (UQ) provides measures of uncertainty, such as an estimate of the \emph{confidence} in an LLM&#39;s generated output, and is therefore increasingly recognized as a crucial component of trusted AI systems. \emph{Black-box} UQ methods do not require access to internal model information from the generating LLM, and therefore have numerous real-world advantages, such as robustness to system changes, adaptability to choice of LLM, reduced costs, and computational tractability. In this paper, we investigate the effectiveness of UQ techniques that are primarily but not necessarily entirely black-box, where the consistency between a generated output and other sampled generations is used as a proxy for confidence in its correctness. We propose a high-level non-verbalized \emph{similarity-based aggregation} framework that subsumes a broad swath of UQ approaches suitable for complex generative tasks, as well as introduce specific novel techniques from the framework that train confidence estimation models using small training sets. Through an empirical study with datasets spanning the diverse tasks of question answering, summarization, and text-to-SQL, we demonstrate that our proposed similarity-based methods result in better calibrated confidences than baselines.

EMNLP 2025

SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models

data-efficient training

code generation and understanding

calibration/uncertainty

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

ACL 2026

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

When does a large language model (LLM) know what it does not know? Uncertainty quantification (UQ) provides measures of uncertainty, such as an estimate of the \emph{confidence} in an LLM's generated output, and is therefore increasingly recognized as a crucial component of trusted AI systems. \emph{Black-box} UQ methods do not require access to internal model information from the generating LLM, and therefore have numerous real-world advantages, such as robustness to system changes, adaptability to choice of LLM, reduced costs, and computational tractability. In this paper, we investigate the effectiveness of UQ techniques that are primarily but not necessarily entirely black-box, where the consistency between a generated output and other sampled generations is used as a proxy for confidence in its correctness. We propose a high-level non-verbalized \emph{similarity-based aggregation} framework that subsumes a broad swath of UQ approaches suitable for complex generative tasks, as well as introduce specific novel techniques from the framework that train confidence estimation models using small training sets. Through an empirical study with datasets spanning the diverse tasks of question answering, summarization, and text-to-SQL, we demonstrate that our proposed similarity-based methods result in better calibrated confidences than baselines.

poster

## 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*

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

Recommendation systems play a critical role in shaping user experiences and access to digital content. However, these systems can exhibit unfair behavior when their performance varies across user groups, especially in linguistically diverse populations. Recent advances in NLP have enabled the identification of user dialects, allowing for more granular analysis of such disparities. In this work, we investigate fairness disparities in recommendation quality among Arabic-speaking users, a population whose dialectal diversity is underrepresented in recommendation system research. By uncovering performance gaps linked to dialectal variation, we highlight the intersection of NLP and recommendation system and underscore the broader social impact of NLP. Our findings emphasize the importance of interdisciplinary approaches in building fair systems, particularly for global and local platforms serving diverse Arabic-speaking communities. The anonymized source code is available at https://anonymous.4open.science/r/FairArRecSys-E619/

Mind the Dialect: NLP Advancements Uncover Fairness Disparities for Arabic Users in Recommendation Systems

In text-video retrieval, auxiliary captions are often used to enhance video understanding, bridging the gap between the modalities. Recently, with the remarkable capabilities in multi-modal understanding, retrieval with MLLMs has emerged as a promising direction. However, we identify two key limitations: (1) retrieval models often fail to effectively leverage the auxiliary captions, neglecting the semantic distinction between the caption (as contextual knowledge) and text queries (as retrieval targets); and (2) auxiliary captions are not typically tailored for retrieval, evaluated with language generation metrics such as BLEU that misalign with retrieval objectives, which require fine-grained discrimination. To address these challenges, we propose CaRe-DPO, a retrieval framework that integrates two key components. First, retrieval role-embeddings are introduced to explicitly differentiate between the roles of heterogeneous textual inputs, allowing the model to better utilize auxiliary captions during retrieval. Second, we present DualGroup-Direct Preference Optimization (DG-DPO), a novel caption optimization strategy that directly uses retrieval relevance scores to supervise caption quality. Moreover, unlike traditional DPO, DG-DPO incorporates group-level preferences, enabling the model to learn a global retrieval ranking over video-caption pairs. Through extensive experiments, we show that CaRe-DPO significantly improves retrieval performance by effectively utilizing the auxiliary knowledge while generating better captions for retrieval.

Captioning for Text-Video Retrieval via Dual-Group Direct Preference Optimization

Designing a generalist scientific agent capable of performing tasks in laboratory settings to assist researchers has become a key goal in recent Artificial Intelligence (AI) research. Unlike everyday tasks, scientific tasks are inherently more delicate and complex, requiring agents to possess a higher level of reasoning ability, structured and temporal understanding of their environment, and a strong emphasis on safety. Existing approaches often fail to address these multifaceted requirements. To tackle these challenges, we present DAVIS. Unlike traditional retrieval-augmented generation (RAG) approaches, DAVIS incorporates structured and temporal memory, which enables model-based planning. Additionally, DAVIS implements an agentic, multi-turn retrieval system, similar to a human's inner monologue, allowing for a greater degree of reasoning over past experiences. DAVIS demonstrates substantially improved performance on the ScienceWorld benchmark comparing to previous approaches on 8 out of 9 elementary science subjects. In addition, DAVIS's World Model demonstrates competitive performance on the famous HotpotQA and MusiqueQA dataset for multi-hop question answering. To the best of our knowledge, DAVIS is the first RAG agent to employ an interactive retrieval method in a RAG pipeline.

DAVIS: Planning Agent with Knowledge Graph-Powered Inner Monologue

We propose a new, training-free method, Graph Reasoning via Retrieval Augmented Framework (GRRAF), that harnesses retrieval-augmented generation (RAG) alongside the code-generation capabilities of large language models (LLMs) to address a wide range of graph reasoning tasks. In GRRAF, the target graph is stored in a graph database, and the LLM is prompted to generate executable code queries that retrieve the necessary information. This approach circumvents the limitations of existing methods that require extensive finetuning or depend on predefined algorithms, and it incorporates an error feedback loop with a time-out mechanism to ensure both correctness and efficiency. Experimental evaluations on the GraphInstruct dataset reveal that GRRAF achieves 100% accuracy on most graph reasoning tasks, including cycle detection, bipartite graph checks, shortest path computation, and maximum flow, while maintaining consistent token costs regardless of graph sizes. Imperfect but still very high performance is observed on subgraph matching. Notably, GRRAF scales effectively to large graphs with up to 10,000 nodes.

Zero-shot Graph Reasoning via Retrieval Augmented Framework with LLMs

The influence of personas on Large Language Models (LLMs) has been widely studied, yet their direct impact on performance remains uncertain. This work explores a novel approach to guiding LLM behaviour through role vectors, an alternative to persona-based prompting. We construct 29 role vectors derived from model activations and evaluate their impact on benchmark performance across multiple domains. Our analysis investigates whether these vectors can effectively steer models toward domain-specific expertise. We measure two key interventions: (i) activation addition, which reinforces role-specific directions, and (ii) directional ablation, which removes them. Results on well-established benchmarks indicate that role vectors do, in fact, influence model behaviour, improving task performance in relevant domains while marginally affecting unrelated tasks. This, in turn, suggests that manipulating internal model representations has a greater impact on outcomes than persona-based prompting.

Can Role Vectors Affect LLM Behaviour?

We investigate the effect of duplicating multihead self-attention (MHSA) layers in large language models (LLMs) across a range of language tasks, with and without fine-tuning. The results demonstrate that duplicating the initial layers once or twice often yields a significant performance boost. Attention analysis uncovered the underlying mechanisms driving the improvement when performing layer duplication. This method enhances LLM capabilities with or without additional training or labeled data.

Layer Duplication in LLMs

The past year has seen an increase in the number of large (parameter) mixture-of-expert (MoE) models in the open domain. With the increase in size has come an increase in capabilities, with the largest models achieving new state-of-the-art on mathematics and reasoning benchmarks. Although the benefit of the MoE architecture can be understood through an engineering efficiency lens, prior work has also investigated whether MoE models exhibit functional differentiation along architectural lines, by examining patterns in the routing behavior of MoE modules. This work investigates whether expert routing in large MoE models is related to the _semantics_ of the inputs. We develop a pair of controlled experiments to identify whether routing occurs on the basis of _semantics_, i.e. the meaning of the inputs. The first experiment compares the activations on lexically identical but semantically distinct inputs, by using pairs of sentences where a common target word either has the same meaning or not. The second experiment compares activations where context is kept constant but the target word is substituted for semantically equivalent/distinct words. By comparing the rate of overlap in expert routing between sentence pairs where meaning is kept the same versus sentence pairs where meaning is changed, we identify whether expert routing is made on the basis of semantics. Our experiments show clear and statistically significant evidence of _semantic routing_ in large MoE models; inputs with the same meaning have greater overlap in routed experts than inputs with differing meaning.

Probing Semantic Routing in Large Mixture-of-Expert Models

Digital tool-based agents that invoke external Application Programming Interfaces (APIs) often rely on documentation to understand API functionality. However, such documentation is frequently missing, outdated, privatized, or inconsistent—hindering the development of reliable, general-purpose agents. In this work, we propose learning API functionality directly from demonstrations as a new paradigm applicable in scenarios without documentation. Using existing API benchmarks, we collect demonstrations from both expert API-based agents and from self-exploration. To understand what information demonstrations must convey for successful task completion, we extensively study how the number of demonstrations and the use of LLM-generated summaries and evaluations affect the task success rate of the API-based agent. Our experiments across datasets and models show that learning functionality from demonstrations remains a non-trivial challenge, even for state-of-the-art LLMs. We find that providing explicit function calls and natural language critiques significantly improves the agent’s task success rate due to more accurate parameter filling. We analyze failure modes, identify sources of error, and highlight key open challenges for future work in documentation-free, self-improving, API-based agents.

Learning API Functionality from In-Context Demonstrations for Tool-based Agents

Recent work has investigated the capabilities of large language models (LLMs) as zero-shot models for generating individual-level characteristics (e.g., to serve as risk models or augment survey datasets). However, when should a user have confidence that an LLM will provide high-quality predictions for their particular task? To address this question, we conduct a large-scale empirical study of LLMs' zero-shot predictive capabilities across a wide range of tabular prediction tasks. We find that LLMs' performance is highly variable, both on tasks within the same dataset and across different datasets. However, when the LLM performs well on the base prediction task, its predicted probabilities become a stronger signal for individual-level accuracy. Then, we construct metrics to predict LLMs' performance at the task level, aiming to distinguish between tasks where LLMs may perform well and where they are likely unsuitable. We find that some of these metrics, each of which are assessed without labeled data, yield strong signals of LLMs' predictive performance on new tasks.

Predicting Language Models’ Success at Zero-Shot Probabilistic Prediction

A dangerous assumption that can be made from prior work on the bias transfer hypothesis (BTH) is that biases do not transfer from pre-trained large language models (LLMs) to adapted models. We invalidate this assumption by studying the BTH in causal models under prompt adaptations, as prompting is an extremely popular and accessible adaptation strategy used in real-world applications. In contrast to prior work, we find that biases can transfer through prompting and that popular prompt-based mitigation methods do not consistently prevent biases from transferring. Specifically, the correlation between intrinsic biases and those after prompt adaptation remained moderate to strong across demographics and tasks: gender (rho >= 0.94) in co-reference resolution, and for age (rho >= 0.98), religion (rho >= 0.69), etc., in question answering. Further, we find that biases remain strongly correlated when varying few-shot composition parameters, such as sample size, stereotypical content, occupational distribution and representational balance (rho >= 0.90). We evaluate several prompt-based debiasing strategies and find that different approaches have distinct strengths, but none consistently reduce bias transfer across models, tasks or demographics. These results demonstrate that correcting bias, and potentially improving reasoning ability, in intrinsic models may be reliable ways to prevent propagation of biases to downstream tasks.

Downloads

Next from EMNLP 2025

Mind the Dialect: NLP Advancements Uncover Fairness Disparities for Arabic Users in Recommendation Systems

Similar lecture

Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities