China

In this paper, we propose the first quantitative measure for translationese---the translationese-index (T-index) for graded and generalizable measurement of translationese, computed from the likelihood ratios of two contrastively fine-tuned language models (LMs). We use a synthesized dataset and a dataset with translations in the wild to evaluate T-index&#39;s generalizability in cross-domain settings and its validity against human judgments. Our results show that T-index is both robust and efficient. T-index scored by two 0.5B LMs fine-tuned on only 1-5k pairs of synthetic data can well capture translationese in the wild. We find that the relative differences in T-indices between translations can well predict pairwise translationese annotations obtained from human annotators; and the absolute values of T-indices correlate well with human ratings of degrees of translationese (pearson r=0.568). Additionally, the correlation between T-index and existing machine translation (MT) quality estimation (QE) metrics such as BLEU and COMET is low, suggesting that T-index is not covered by these metrics and can serve as a complementary metric in MT QE. All our code and data will be released upon acceptance.

EMNLP 2025

Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese

In this paper, we propose the first quantitative measure for translationese---the translationese-index (T-index) for graded and generalizable measurement of translationese, computed from the likelihood ratios of two contrastively fine-tuned language models (LMs). We use a synthesized dataset and a dataset with translations in the wild to evaluate T-index's generalizability in cross-domain settings and its validity against human judgments. Our results show that T-index is both robust and efficient. T-index scored by two 0.5B LMs fine-tuned on only 1-5k pairs of synthetic data can well capture translationese in the wild. We find that the relative differences in T-indices between translations can well predict pairwise translationese annotations obtained from human annotators; and the absolute values of T-indices correlate well with human ratings of degrees of translationese (pearson r=0.568). Additionally, the correlation between T-index and existing machine translation (MT) quality estimation (QE) metrics such as BLEU and COMET is low, suggesting that T-index is not covered by these metrics and can serve as a complementary metric in MT QE. All our code and data will be released upon acceptance.

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."<br>

*Message from the General Chair, Dirk Hovy*

[**Link to Conference Handbook**](https://drive.google.com/file/d/1johU5QqVVYO4RfH7QcIORr7qrVBdzdwC/view?usp=sharing)





<br>

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

Information retrieval models that aim to search for documents relevant to a query have shown multiple successes, which have been applied to diverse tasks. Yet, the query from the user is oftentimes short, which challenges the retrievers to correctly fetch relevant documents. To tackle this, previous studies have proposed expanding the query with a couple of additional (user-related) features related to it. However, they may be suboptimal to effectively augment the query, and there is plenty of other information available to augment it in a relational database. Motivated by this fact, we present a novel retrieval framework called Database-Augmented Query representation (DAQu), which augments the original query with various (query-related) metadata across multiple tables. In addition, as the number of features in the metadata can be very large and there is no order among them, we encode them with the graph-based set-encoding strategy, which considers hierarchies of features in the database without order. We validate our DAQu in diverse retrieval scenarios, demonstrating that it significantly enhances overall retrieval performance over relevant baselines.

Database-Augmented Query Representation for Information Retrieval

Late-interaction based multi-vector retrieval systems have greatly advanced the field of information retrieval by enabling fast and accurate search over millions of documents. However, these systems rely on a naive summation of token-level similarity scores which often leads to inaccurate relevance estimation caused by the tokenization of semantic units (e.g., words and phrases) and the influence of low-content words (e.g., articles and prepositions). To address these challenges, we propose **TRIAL**: **T**oken **R**elations and **I**mportance **A**ware **L**ate-interaction, which enhances late interaction by explicitly modeling token relations and token importance in relevance scoring. Extensive experiments on three widely used benchmarks show that TRIAL achieves state-of-the-art accuracy, with an nDCG@10 of 46.3 on MSMARCO (in-domain), and average nDCG@10 scores of 51.09 and 72.15 on BEIR and LoTTE Search (out-of-domain), respectively. With superior accuracy, TRIAL maintains competitive retrieval speed compared to existing late-interaction methods, making it a practical solution for large-scale text retrieval.

TRIAL: Token Relations and Importance Aware Late-interaction for Accurate Text Retrieval

Understanding long-form videos, such as movies and TV episodes ranging from tens of minutes to two hours, remains a major challenge for multi-modal models. Existing benchmarks often fall short in testing the full range of cognitive skills needed to process these temporally rich and narratively complex inputs. We introduce InfiniBench, a comprehensive benchmark designed to rigorously evaluate the capabilities of models in long video understanding. InfiniBench offers: (1) Over 1,000 hours of video content, with an average video length of 52.59 minutes, (2) The largest set of question-answer pairs for long video comprehension, totaling around \totalSampleNumber, (3) Eight diverse skills that span both grounding-based (e.g., scene transitions, character actions) and reasoning-based (e.g., deep context, multi-event linking) understanding, and (4) Rich annotation formats, including both multiple-choice and open-ended questions. We conduct an in-depth evaluation across both commercial (GPT-4o, Gemini 1.5 Flash) and open-source (Qwen2.5-VL, InternVL2.5) vision-language models. Results reveal that current models remain far from solving long video understanding: on grounding-based skills, the top open-source model (Qwen2.5-VL) and GPT-4o achieve only 39.4% and 48.1% accuracy, respectively. Interestingly, several models achieve non-trivial performance using only the movie or episode title, without watching the video, revealing a reliance on pre-trained world knowledge that partially compensates for the absence of visual or temporal understanding. These findings highlight critical gaps in current approaches and underscore the need for models that truly engage with long visual narratives.

InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows

Despite significant advancements in Large Vision Language Models (LVLMs), a gap remains, particularly regarding their interpretability and how they locate and interpret textual information within images. In this paper, we explore various LVLMs to identify the specific heads responsible for recognizing text from images, which we term the Optical Character Recognition Head (\textbf{OCR Head}). Our findings regarding these heads are as follows: (1) Less Sparse: Unlike previous retrieval heads, a large number of heads are activated to extract textual information from images. (2) Qualitatively Distinct: OCR heads possess properties that differ significantly from general retrieval heads, exhibiting low similarity in their characteristics. (3) Statically Activated: The frequency of activation for these heads closely aligns with their OCR scores. We validate our findings in downstream tasks by applying Chain-of-Thought (CoT) to both OCR and conventional retrieval heads and by masking these heads. We also demonstrate that redistributing sink-token values within the OCR heads improves performance. These insights provide a deeper understanding of the internal mechanisms LVLMs employ in processing embedded textual information in images.

How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads

We report on investigations into the characteristics of outgoing connections in feedforward layers of large language models. Our findings show that inner neurons with diverse outgoing connection strengths contribute more significantly to model performance than those with uniform connections. We propose a new fine-tuning loss that takes advantage of this observation by decreasing the outgoing connection entropy in feedforward layers. Using this loss yields gains over standard fine-tuning across two different model families (PaLM-2 and Gemma-2) for downstream tasks in math, coding, and language understanding. To further elucidate the role of outgoing connection heterogeneity, we develop a data-free structured pruning method, which uses entropy to identify and remove neurons. This method significantly surpasses the effectiveness of random and even magnitude-based neuron removal.

The Role of Outgoing Connection Heterogeneity in Feedforward Layers of Large Language Models

Extracting individual sentences from a document as evidence or reasoning steps is commonly done in many NLP tasks. However, extracted sentences often lack context necessary to make them understood, e.g., coreference and background information. To this end, we propose a content selection and planning framework for zero-shot decontextualisation, which determines what content should be mentioned and in what order for a sentence to be understood out of context. Specifically, given a potentially ambiguous sentence and its context, we first segment it into basic semantically-independent units. We then identify potentially ambiguous units from the given sentence, and extract relevant units from the context based on their discourse relations. Finally, we generate a content plan to rewrite the sentence by enriching each ambiguous unit with its relevant units. Experimental results demonstrate that our approach is competitive for sentence decontextualisation, producing sentences that exhibit better semantic integrity and discourse coherence, outperforming existing methods.

Improving Zero-shot Sentence Decontextualisation with Content Selection and Planning

In this paper, we study the surprising impact that truncating text embeddings has on downstream performance. We consistently observe across 6 state-of-the-art text encoders and 26 downstream tasks, that randomly removing up to 50% of embedding dimensions results in only a minor drop in performance, less than 10%, in retrieval and classification tasks. Given the benefits of using smaller-sized embeddings, as well as the potential insights about text encoding, we study this phenomenon and find that, contrary to what is suggested in prior work, this is not the result of an ineffective use of representation space. Instead, we find that a large number of uniformly distributed dimensions actually cause an increase in performance when removed. This would explain why, on average, removing a large number of embedding dimensions results in a marginal drop in performance. We make similar observations when truncating the embeddings used by large language models to make next-token predictions on generative tasks, suggesting that this phenomenon is not isolated to classification or retrieval tasks.

Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks

Minimum Bayes Risk (MBR) decoding has seen renewed interest as an alternative to traditional generation strategies. While MBR has proven effective in machine translation, where the variability of a language model's outcome space is naturally constrained, it may face challenges in more open-ended tasks such as dialogue or instruction-following. We hypothesise that in such settings, applying MBR with standard similarity-based utility functions may result in selecting responses that are broadly representative of the model's distribution, yet sub-optimal with respect to any particular grouping of generations that share an underlying latent structure. In this work, we introduce three lightweight adaptations to the utility, designed to make MBR more sensitive to structural variability in the outcome space. To test our hypothesis, we curate a dataset capturing three representative types of latent structure: dialogue act, emotion, and response structure. We also propose two metrics to evaluate the structural optimality of MBR. Our analysis demonstrates that common utility functions fall short by these metrics. In contrast, our proposed adaptations considerably improve structural optimality. Finally, we evaluate our approaches on real-world instruction-following benchmarks, AlpacaEval and MT-Bench, and show that increased structural sensitivity improves generation quality by up to 13.7 percentage points in win rate.

Structure-Conditional Minimum Bayes Risk Decoding

Large Language Models (LLMs) are increasingly deployed across diverse domains but often exhibit disparities in how they handle real life queries. To systematically investigate these effects with various disability context, we introduce AccessEval, a large-scale benchmark evaluating total 21 close & open source LLMs across six real-world domains and nine disability types using paired Neutral and Disability-Aware Queries. We evaluated model outputs with metrics for factual accuracy, sentiment, and social perception. Our analysis reveals that responses to disability-aware queries tend to have higher factual error, more negative tone, and increased stereotyping with social perception compared to neutral queries. These effects show notable variation by domain and disability type. Disabilities affecting hearing, speech and mobility are disproportionately impacted. These disparities reveal persistent forms of ableism, highlighting the need for more comprehensive and nuanced assessment. We further argue that framing bias in terms of model performance within real-world decision making helps to better link model behaviors to the potential harms users may face. This approach guides the development of more effective and tailored fairness interventions. AccessEval, therefore, serves as a crucial tool for advancing equitable and inclusive language technologies.

AccessEval: Benchmarking Disability Bias in Large Language Models

The affective attitude of liking a recommended item reflects just one category in a wide spectrum of affective phenomena that also includes emotions such as entranced or intrigued, moods such as cheerful or buoyant, as well as more fine-grained affective states, such as "pleasantly surprised by the conclusion". In this paper, we introduce a novel recommendation task that can leverage a virtually unbounded range of affective states sought explicitly by the user in order to identify items that, upon consumption, are likely to induce those affective states. Correspondingly, we create a large dataset of user preferences containing expressions of fine-grained affective states that are mined from book reviews, and propose a Transformer-based architecture that leverages such affective expressions as input. We then use the resulting dataset of affective states preferences, together with the linked users and their histories of book readings, ratings, and reviews, to train and evaluate multiple recommendation models on the task of matching recommended items with affective preferences. Experiments show that the best results are obtained by models that can utilize textual descriptions of items and user affective preferences.

Downloads

Next from EMNLP 2025

Database-Augmented Query Representation for Information Retrieval

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES