Austria

In search settings, calibrating the scores during the ranking process to quantities such as click-through rates or relevance levels enhances a system&#39;s usefulness and trustworthiness for downstream users. While previous research has improved this notion of calibration for low complexity learning-to-rank models, the larger data demands and parameter count specific to modern neural text rankers produce unique obstacles that hamper the efficacy of methods intended for the learning-to-rank setting.

This paper proposes exploiting large language models (LLMs) to provide relevance and uncertainty signals for these neural text rankers to produce scale-calibrated scores through Monte Carlo sampling of natural language explanations (NLEs). Our approach transforms the neural ranking task from ranking textual query-document pairs to ranking corresponding synthesized NLEs. Comprehensive experiments on two popular document ranking datasets show that the NLE-based calibration approach consistently outperforms past calibration methods and LLM-based methods for ranking, calibration, and query performance prediction tasks.

ACL 2025

Explain then Rank: Scale Calibration of Neural Rankers Using Natural Language Explanations from LLMs

llms

calibration

ranking

search

information retrieval

## 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.

In search settings, calibrating the scores during the ranking process to quantities such as click-through rates or relevance levels enhances a system's usefulness and trustworthiness for downstream users. While previous research has improved this notion of calibration for low complexity learning-to-rank models, the larger data demands and parameter count specific to modern neural text rankers produce unique obstacles that hamper the efficacy of methods intended for the learning-to-rank setting.

This paper proposes exploiting large language models (LLMs) to provide relevance and uncertainty signals for these neural text rankers to produce scale-calibrated scores through Monte Carlo sampling of natural language explanations (NLEs). Our approach transforms the neural ranking task from ranking textual query-document pairs to ranking corresponding synthesized NLEs. Comprehensive experiments on two popular document ranking datasets show that the NLE-based calibration approach consistently outperforms past calibration methods and LLM-based methods for ranking, calibration, and query performance prediction tasks.

poster

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s 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.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

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 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Dense embeddings are fundamental to modern machine learning systems, powering Retrieval-Augmented Generation (RAG), information retrieval, and representation learning. While instruction-conditioning has become the dominant approach for embedding specialization, its direct application to low-capacity models imposes fundamental representational constraints that limit the performance gains derived from specialization. In this paper, we analyze these limitations and introduce the Mixture of Task Experts (MoTE) transformer block, which leverages task-specialized parameters trained with Task-Aware Contrastive Learning (TACL) to enhance the model's ability to generate specialized embeddings. Empirical results show that MoTE achieves 64% higher performance gains in retrieval datasets (+3.27 -> +5.21) and 43% higher performance gains across all datasets (+1.81 -> 2.60). Critically, these gains are achieved without altering instructions, training data, inference time, or number of active parameters.

Beyond instruction-conditioning, MoTE: Mixture of Task Experts for Multi-task Embedding Models

The challenge of developing agents capable of open-world planning remains fundamental to artificial general intelligence (AGI). While large language models (LLMs) have made progress with their vast world knowledge, their limitations in perception, memory, and reliable reasoning still hinder LLM-based agents from achieving human-level performance in long-term tasks. Drawing inspiration from human cognitive-metacognitive collaboration, we propose \textbf{Metagent-P}, integrating the world knowledge of LLMs, the symbolic reasoning capabilities of cognitive architectures, and the self-reflection characteristic of metacognition to construct a “planning-verification-execution-reflection” framework. Metagent-P improves experience utilization through multimodal memory integration. It uses a neural-symbolic hierarchical representation structure to ensure the plan's reasoning correctness in advance. Finally, it actively adapts the agent to dynamic environments through monitoring, evaluation, and regulation mechanisms. Experimental results show Metagent-P significantly outperforms current state-of-the-art methods in Minecraft. In long-term tasks, Metagent-P reduces the average replanning counts by \textbf{34%} and exceeds the average human success rate by \textbf{18.96%}. Additionally, Metagent-P also demonstrates self-evolution through step-by-step open-world exploration.

Metagent-P: A Neuro-Symbolic Planning Agent with Metacognition for Open Worlds

Query-driven recommendation with unknown items poses a challenge for users to understand why certain items are appropriate for their needs. Query-driven Contrastive Summarization (QCS) is a methodology designed to address this issue by leveraging language-based item descriptions to clarify contrasts between them. However, existing state-of-the-art contrastive summarization methods such as STRUM-LLM fall short of this goal. To overcome these limitations, we introduce Q-STRUM Debate, a novel extension of STRUM-LLM that employs debate-style prompting to generate focused and contrastive summarizations of item aspects relevant to a query. Leveraging modern large language models (LLMs) as powerful tools for generating debates, Q-STRUM Debate provides enhanced contrastive summaries. Experiments across three datasets demonstrate that Q-STRUM Debate yields significant performance improvements over existing methods on key contrastive summarization criteria, thus introducing a novel and performant debate prompting methodology for QCS.

Q-STRUM Debate: Query-Driven Contrastive Summarization for Recommendation Comparison

Automatic depression detection provides cues for early clinical intervention by clinicians. Clinical interviews for depression detection involve dialogues centered around multiple themes. Existing studies primarily design end-to-end neural network models to capture the hierarchical structure of clinical interview dialogues. However, these methods exhibit defects in modeling the thematic content of clinical interviews: 1) they fail to explicitly capture intra-theme and inter-theme correlation, and 2) they do not allow clinicians to intervene and focus on themes of interest. To address these issues, this paper introduces an interactive depression detection framework, namely Predicting Depression in Screening Interviews from Interactive Multi-Theme Collaboration (PDIMC). PDIMC leverages in-context learning techniques to identify themes in clinical interviews and then models both intra-theme and inter-theme correlation. Additionally, it employs AI-driven feedback to simulate the interests of clinicians, enabling interactive adjustment of theme importance. PDIMC achieves absolute improvements of 12% on Recall and 35% on F1-dep. metrics, compared to the previous state-of-the-art model on the depression detection dataset DAIC-WOZ, which demonstrates the effectiveness of capturing theme correlation and incorporating interactive external feedback.

Predicting Depression in Screening Interviews from Interactive Multi-Theme Collaboration

As large language models (LLMs) become increasingly integrated into critical applications, aligning their behavior with human values presents significant challenges. Current methods, such as Reinforcement Learning from Human Feedback (RLHF), typically focus on a limited set of coarse-grained values and are resource-intensive. Moreover, the correlations between these values remain implicit, leading to unclear explanations for value-steering outcomes. Our work argues that a latent causal value graph underlies the value dimensions of LLMs and that, despite alignment training, this structure remains significantly different from human value systems. We leverage these causal value graphs to guide two lightweight value-steering methods: role-based prompting and sparse autoencoder (SAE) steering, effectively mitigating unexpected side effects. Furthermore, SAE provides a more fine-grained approach to value steering. Experiments on Gemma-2B-IT and Llama3-8B-IT demonstrate the effectiveness and controllability of our methods.

Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective

Semantic role labeling (SRL) is a crucial task of natural language processing (NLP). Although generative decoder-based large language models (LLMs) have achieved remarkable success across various NLP tasks, they still lag behind state-of-the-art encoder-decoder (BERT-like) models in SRL. In this work, we seek to bridge this gap by equipping LLMs for SRL with two mechanisms: (a) retrieval-augmented generation and (b) self-correction. The first mechanism enables LLMs to leverage external linguistic knowledge such as predicate and argument structure descriptions, while the second allows LLMs to identify and correct inconsistent SRL outputs. We conduct extensive experiments on three widely-used benchmarks of SRL (CPB1.0, CoNLL-2009, and CoNLL-2012). Results demonstrate that our method achieves state-of-the-art performance in both Chinese and English, marking the first successful application of LLMs to surpass encoder-decoder approaches in SRL.

LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Models

Constrained by the cost and ethical concerns of involving real seekers in AI-driven mental health, researchers develop LLM-based conversational agents (CAs) with tailored configurations, such as profiles, symptoms, and scenarios, to simulate seekers. While these efforts advance AI in mental health, achieving more realistic seeker simulation remains hindered by two key challenges: dynamic evolution and multi-session memory. Seekers' mental states often fluctuate during counseling, which typically spans multiple sessions. To address this, we propose **AnnaAgent**, an emotional and cognitive dynamic agent system equipped with tertiary memory. AnnaAgent incorporates an emotion modulator and a complaint elicitor trained on real counseling dialogues, enabling dynamic control of the simulator's configurations. Additionally, its tertiary memory mechanism effectively integrates short-term and long-term memory across sessions. Evaluation results, both automated and manual, demonstrate that AnnaAgent achieves more realistic seeker simulation in psychological counseling compared to existing baselines. The ethically reviewed and screened code can be found on [Anonymous Github](https://anonymous.4open.science/r/AnnaAgent-9041).

AnnaAgent: Dynamic Evolution Agent Systerm with Multi-Session Memory for Realistic Seeker Simulation

Natural language understanding systems struggle with low-resource languages, including many dialects of high-resource ones. Dialect-to-standard normalization attempts to tackle this issue by transforming dialectal text so that it can be used by standard-language tools downstream. In this study, we tackle this task by introducing a new normalization method that combines rule-based linguistically informed transformations and large language models (LLMs) with targeted few-shot prompting, without requiring any parallel data. We implement our method for Greek dialects and apply it on a dataset of regional proverbs, evaluating the outputs using human annotators. We then use this dataset to conduct downstream experiments, finding that previous results regarding these proverbs relied solely on superficial linguistic information, including orthographic artifacts, while new observations can still be made through the remaining semantics.

Dialect Normalization using Large Language Models and Morphological Rules

Pragmatic reasoning—the ability to infer meaning beyond literal interpretation—is crucial for social cognition and communication. While LLMs have been benchmarked for their pragmatic understanding, improving their performance remains underexplored. Existing methods rely on annotated labels but overlook the reasoning process humans naturally use to interpret implicit meaning. To bridge this gap, we introduce a novel pragmatic dataset that includes *explicit reasoning (thoughts)* for both correct and incorrect interpretations. Through preference-tuning and supervised fine-tuning, we demonstrate that thought-based learning significantly enhances LLMs' pragmatic understanding, improving accuracy by 11.12% across model families. We further discuss a transfer-learning study where we evaluate the performance of *thought*- based training for the tasks not seen during the train time, and observed an improvement of 16.10% compared to *label* trained models.

Understand the Implication: Learning to Think for Pragmatic Understanding

Pre-trained language models (PLMs) fragment numerals and units that express quantities in arbitrary ways, depending on their subword vocabulary. Consequently, they are unable to contextualize the fragment embeddings well enough to be proficient with dense retrieval in domains like e-commerce and finance. Arithmetic inequality constraints (``laptop under 2 lb'') offer additional challenges. In response, we propose DeepQuant, a dense retrieval system built around a dense multi-vector index, but carefully engineered to elicit and exploit quantities and associated comparison intents. A novel component of our relevance score compares two quantities with compatible units, conditioned on a proposed comparison operator. The uncertain extractions of numerals, units and comparators are marginalized in a suitable manner. On two public and one proprietary e-commerce benchmark, DeepQuant is both faster and more accurate than popular PLMs. It also beats several competitive sparse and dense retrieval systems that do not take special cognizance of quantities.

Downloads

Next from ACL 2025

Beyond instruction-conditioning, MoTE: Mixture of Task Experts for Multi-task Embedding Models

Similar lecture

Calibrating Language Models for Neural Ranking under Noisy Supervision with Relaxed Labels