China

Large language model (LLM)-based embedding models, benefiting from large scale pre-training and post-training, have begun to surpass BERT and T5-based models on general-purpose text embedding tasks such as document retrieval. However, a fundamental limitation of LLM embeddings lies in the unidirectional attention used during autoregressive pre-training, which misaligns with the bidirectional nature of text embedding tasks. To this end, We propose adopting diffusion language models for text embeddings, motivated by their inherent bidirectional architecture and recent success in matching or surpassing LLMs especially on reasoning tasks. We present the first systematic study of the diffusion language embedding model, which outperforms the LLM-based embedding model by 20% on long-document retrieval, 8% on reasoning-intensive retrieval, 2% on instruction-following retrieval, and achieve competitive performance on traditional text embedding benchmarks. Our analysis verifies that bidirectional attention is crucial for encoding global context in long and complex text.

EMNLP 2025

Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective

diffusion language models

embedding models

text retrieval

### 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**. 

ACL 2025

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

technical paper

## 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.

Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase performance on standard benchmarks, this may partly be due to overfitting effects, which would confound an understanding of their true capability. In this work, we scrutinize the robustness of reward models and the extent of such overfitting. We build reWordBench, which systematically transforms reward model inputs in meaning- or ranking-preserving ways. We show that state-of-the-art reward models suffer from substantial performance degradation even with minor input transformations, sometimes dropping to significantly below-random accuracy, suggesting brittleness. To improve reward model robustness, we propose to explicitly train them to assign similar scores to paraphrases, and find that this approach also improves robustness to other distinct kinds of transformations. For example, our robust reward model reduces such degradation by roughly half for the Chat Hard subset in RewardBench. Furthermore, when used in alignment, our robust reward models demonstrate better utility and lead to higher-quality outputs, winning in up to 59% of instances against a standardly trained RM.

reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs

Human listeners readily adjust to unfamiliar speakers and language varieties through exposure, but do these adaptation benefits extend to state-of-the-art spoken language models (SLMs)? We introduce a scalable framework that allows for in-context learning (ICL) in Phi-4 Multimodal (Phi-4-MM) using interleaved task prompts and audio-text pairs, and find that as few as 12 example utterances (~50 seconds) at inference time reduce word error rates by a relative 19.7% (1.2 pp.) on average across diverse English corpora. These improvements are most pronounced in low-resource varieties, when the context and target speaker match, and when more examples are provided—though scaling our procedure yields diminishing marginal returns to context length. Overall, we find that our novel ICL adaptation scheme (1) reveals a similar performance profile to human listeners, and (2) demonstrates consistent improvements to automatic speech recognition (ASR) robustness across diverse speakers and language backgrounds. While adaptation succeeds broadly, significant gaps remain for certain varieties, revealing where current models still fall short of human flexibility. We release our prompts and code on GitHub.

In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties

End-to-end Large Speech Language Models (LSLMs) have demonstrated impressive conversational generation abilities, yet consistently fall short of traditional pipeline systems on semantic understanding benchmarks. In this work, we reveal through systematic experimentation that although LSLMs lose some text input performance after speech-text alignment training, the performance gap between speech and text inputs is more pronounced, which we refer to as the modality gap. To understand this gap, we analyze both coarse- and fine-grained text and speech representations. At the coarse-grained level, representations of speech and text in deeper layers are found to be increasingly aligned in direction (cosine similarity), while concurrently diverging in magnitude (Euclidean distance). We further find that representation similarity is strongly correlated with the modality gap. At the fine-grained level, a spontaneous token-level alignment pattern between text and speech representations is observed. Based on this, we introduce the Alignment Path Score to quantify token-level alignment quality, which exhibits stronger correlation with the modality gap. Building on these insights, we design targeted interventions on critical tokens through angle projection and length normalization. These strategies demonstrate the potential to improve correctness for speech inputs. Our study provides the first systematic empirical analysis of the modality gap and alignment mechanisms in LSLMs, offering both theoretical and methodological guidance for future optimization.

Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models

Self-taught reasoners (STaRs) enhance the mathematical reasoning abilities of large language models (LLMs) by leveraging self-generated responses for self-training. Recent studies have incorporated reward models to guide response selection or decoding, aiming to obtain higher-quality data. However, they typically allocate a uniform sampling budget across all problems, overlooking the varying utility of problems at different difficulty levels. In this work, we conduct an empirical study and find that problems near the boundary of the LLM’s reasoning capability offer significantly greater learning utility than both easy and overly difficult ones. To identify and exploit such problems, we propose HS-STaR, a Hierarchical Sampling framework for Self-Taught Reasoners. Given a fixed sampling budget, HS-STaR first performs lightweight pre-sampling with a reward-guided difficulty estimation strategy to efficiently identify boundary-level problems. Subsequently, it dynamically reallocates the remaining budget toward these high-utility problems during a re-sampling phase, maximizing the generation of valuable training data. Extensive experiments across multiple reasoning benchmarks and backbone LLMs demonstrate that HS-STaR significantly outperforms other baselines without requiring additional sampling budget.

HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation

Rumor detection on social media has become crucial due to the rapid spread of misinformation. Existing approaches primarily focus on within-domain tasks, resulting in suboptimal performance in cross-domain scenarios due to domain shift. To address this limitation, we draw inspiration from the strong generalization capabilities of Test-Time Adaptation (TTA) and propose a novel framework to enhance rumor detection performance across different domains. Specifically, we introduce Test-Time Adaptation for Rumor Detection (T²ARD), which incorporates both sigle-domain model and target graph adaptation strategies tailored to the unique requirements of cross-domain rumor detection. T²ARD utilizes a graph adaptation module that updates the graph structure and node attributes through multi-level self-supervised contrastive learning, aiming to derive invariant graph representations. To mitigate the impact of significant distribution shifts on self-supervised signals, T²ARD perform model adaptation based on the annotations by Large Language Models (LLMs) in target graph to produce pseudo labels as supervised signals. Experiments conducted on four widely-used cross-domain datasets demonstrate that T²ARD achieves state-of-the-art performance, surpassing existing methods in rumor detection.

Cross-domain Rumor Detection via Test-Time Adaptation and Large Language Models

Knowledge base question answering (KBQA) aims to answer user questions in natural language using rich human knowledge stored in large KBs. As current KBQA methods struggle with unseen knowledge base elements and their novel compositions at test time, we introduce SG-KBQA --- a novel model that injects schema contexts into entity retrieval and logical form generation to tackle this issue. It exploits information about the semantics and structure of the knowledge base provided by schema contexts to enhance generalizability. We show that \model\ achieves strong generalizability, outperforming state-of-the-art models on two commonly used benchmark datasets across a variety of test settings. Our source code is available at \url{https://anonymous.4open.science/r/SG-KBQA-7895}.

Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation

Counterfactual reasoning typically involves considering alternatives to actual events. While often applied to understand past events, a distinct form—forward counterfactual reasoning—focuses on anticipating plausible future developments. This type of reasoning is invaluable in dynamic financial markets, where anticipating market developments can powerfully unveil potential risks and opportunities for stakeholders, guiding their decision-making. However, performing this at scale is challenging due to the cognitive demands involved, underscoring the need for automated solutions. Large Language Models (LLMs) offer promise, but remain unexplored for this application. To address this gap, we introduce a novel benchmark, Fin-Force—**FIN**ancial **FOR**ward **C**ounterfactual **E**valuation. By curating financial news headlines and providing structured evaluation, Fin-Force supports LLM based forward counterfactual generation. This paves the way for scalable and automated solutions for exploring and anticipating future market developments, thereby providing structured insights for decision-making. Through experiments on Fin-Force, we evaluate state-of-the-art LLMs and counterfactual generation methods, analyzing their limitations and proposing insights for future research.

Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation

Large language models (LLMs) have demonstrated impressive performance on reasoning tasks, including mathematical reasoning. However, the current evaluation mostly focuses on carefully constructed benchmarks and neglects the consideration of real-world reasoning problems that present missing or contradictory conditions, known as ill-defined problems. To further study this problem, we develop a large-scale benchmark called Problems with Missing and Contradictory conditions (PMC) containing over 5,000 validated ill-defined mathematical problems. Our preliminary experiments through \benchmark reveal two challenges about existing methods: (1) traditional methods exhibit a trade-off between solving accuracy and rejection capabilities, and (2) formal methods struggle with modeling complex problems. To address these challenges, We develop Variable-Constraint Search (VCSearch), a training-free framework that leverages formal language to detect ill-defined problems, where a variable-constraint pair search strategy is incorporated to improve the modeling capability of formal language. Extensive experiments demonstrate that VCSearch improves the accuracy of identifying unsolvable problems by at least 12% across different LLMs, thus achieving stronger robust mathematical reasoning ability.

VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning

The increasing acceptance of large language models (LLMs) as an alternative to knowledge sources marks a significant paradigm shift across various domains, including time-sensitive fields such as law, healthcare, and finance. To fulfill this expanded role, LLMs must not only be factually accurate but also demonstrate consistency across temporal dimensions, necessitating robust temporal reasoning capabilities. Despite this critical requirement, efforts to ensure temporal consistency in LLMs remain scarce including noticeable absence of endeavors aimed at evaluating or augmenting LLMs across temporal references in time-sensitive inquiries. In this paper, we seek to address this gap by introducing a novel benchmark entitled temporal referential consistency, accompanied by a resource TEMP-ReCon designed to benchmark a wide range of both open-source and closed-source LLMs with various linguistic contexts characterized by differing resource richness (including English, French, and Romanian). The findings emphasis that LLMs do exhibit insufficient temporal referent consistency. To address this, we propose \newmodel, a reasoning path alignment-based model that aims to enhance the temporal referential consistency of LLMs. Our empirical experiments substantiate the efficacy of UnTRaP compared to several baseline models.

Temporal Referential Consistency: Do LLMs Favor Sequences Over Absolute Time References?

Human language use is robust to errors: comprehenders can and do mentally correct utterances that are implausible or anomalous. How are humans able to solve these problems in real time, picking out alternatives from an unbounded space of options using limited cognitive resources? And can language models trained on next-word prediction for typical language be augmented to handle language anomalies in a human-like way? Using a language model as a prior and an error model to encode likelihoods, we use Sequential Monte Carlo with optional rejuvenation to perform incremental and approximate probabilistic inference over intended sentences and production errors. We demonstrate that the model captures previously established patterns in human sentence processing, and that a trade-off between human-like noisy-channel inferences and computational resources falls out of this model. From a psycholinguistic perspective, our results offer a candidate algorithmic model of rational inference in language processing. From an NLP perspective, our results showcase how to elicit reasoning-like behavior from a relatively small LLM while controlling the amount of computation available during inference. Our model is implemented in the Gen.jl probabilistic programming language, and our code is available at \url{https://osf.io/4zyd5/?view_only=54ebfb788ceb4f139f675130e7161111}.

Downloads

Next from EMNLP 2025

reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs

Similar lecture

A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokens

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES