Canada

In this paper, we present LLM-Blender, an innovative ensembling framework designed to attain consistently superior performance by leveraging the diverse strengths and weaknesses of multiple open-source large language models (LLMs). Our framework consists of two complementary modules: PairRanker and GenFuser, addressing the observation that optimal LLMs for different examples can significantly vary. PairRanker employs a specialized pairwise comparison method to distinguish subtle differences between candidate outputs. It jointly encodes the input text and a pair of candidate outputs, utilizing cross-attention encoders to determine the superior candidate. Our results demonstrate that PairRanker exhibits the highest correlation with ChatGPT-based ranking. By aggregating these pairwise comparisons from PairRanker, we can generate a ranking of LLMs for each example. GenFuser then aims to merge the top-ranked candidates, generating an improved output by capitalizing on their strengths and mitigating their weaknesses. To facilitate large scale evaluation, we introduce a benchmark dataset, MixInstruct, which is a mixture of multiple instruction datasets featuring oracle pairwise comparisons for testing purposes. Our LLM-BLENDER significantly surpasses the best LLMs and baseline ensembling methods across various metrics, establishing a substantial performance gap.

&lt;iframe src=&quot;https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/98e3bb1c-7e64-4e09-93af-49fcc90e4e97&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion

langauge generation

decoding

ensemble learning

large language models

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair:<br>
*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.*<br>
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)<br><br><br>



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

In this paper, we present LLM-Blender, an innovative ensembling framework designed to attain consistently superior performance by leveraging the diverse strengths and weaknesses of multiple open-source large language models (LLMs). Our framework consists of two complementary modules: PairRanker and GenFuser, addressing the observation that optimal LLMs for different examples can significantly vary. PairRanker employs a specialized pairwise comparison method to distinguish subtle differences between candidate outputs. It jointly encodes the input text and a pair of candidate outputs, utilizing cross-attention encoders to determine the superior candidate. Our results demonstrate that PairRanker exhibits the highest correlation with ChatGPT-based ranking. By aggregating these pairwise comparisons from PairRanker, we can generate a ranking of LLMs for each example. GenFuser then aims to merge the top-ranked candidates, generating an improved output by capitalizing on their strengths and mitigating their weaknesses. To facilitate large scale evaluation, we introduce a benchmark dataset, MixInstruct, which is a mixture of multiple instruction datasets featuring oracle pairwise comparisons for testing purposes. Our LLM-BLENDER significantly surpasses the best LLMs and baseline ensembling methods across various metrics, establishing a substantial performance gap.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/98e3bb1c-7e64-4e09-93af-49fcc90e4e97" width="300" height="400"></iframe>

poster

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
<br>The conference will be held in Toronto, Canada, July 9-14, 2023.<br><br>
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience.<br>
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**
<br><br><br><br>

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

Despite the growing success of diffusion models in continuous-valued domains (e.g., images), similar efforts for discrete domains such as text have yet to match the performance of autoregressive language models. In this work, we present SSD-LM---a diffusion-based language model with two key design choices. First, SSD-LM is semi-autoregressive, iteratively generating blocks of text, allowing for flexible output length at decoding time while enabling local bidirectional context updates. Second, it is simplex-based, performing diffusion on the natural vocabulary space rather than a learned latent space, allowing us to incorporate classifier guidance and modular control using off-the-shelf classifiers without any adaptation. We evaluate SSD-LM on unconstrained text generation benchmarks, and show that it matches or outperforms strong autoregressive GPT-2 models across standard quality and diversity metrics, while vastly outperforming diffusion-based baselines. On controlled text generation, SSD-LM also outperforms competitive baselines, with an extra advantage in modularity.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/0baeb2a1-26b6-4096-8186-ade6c21d1668" width="300" height="400"></iframe>

SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control

The retrieval model is an indispensable component for real-world knowledge-intensive tasks, e.g., open-domain question answering (ODQA). As separate retrieval skills are annotated for different datasets, recent work focuses on customized methods, limiting the model transfer- ability and scalability. In this work, we propose a modular retriever where individual modules correspond to key skills that can be reused across datasets. Our approach supports flexible skill configurations based on the target domain to boost performance. To mitigate task interference, we design a novel modularization parameterization inspired by sparse Transformer. We demonstrate that our model can benefit from self-supervised pretraining on Wikipedia and fine-tuning using multiple ODQA datasets, both in a multi-task fashion. Our approach outperforms recent self-supervised retrievers in zero-shot evaluations and achieves state-of-the-art fine-tuned retrieval performance on NQ, HotpotQA and OTT-QA.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/d8a26312-66e5-47ce-8966-b47898cbcc4e" width="300" height="400"></iframe>

Chain-of-Skills: A Configurable Model for Open-Domain Question Answering

Tables are widely used in research and business, which are suitable for human consumption, but not easily machine-processable, particularly when tables are present in images.One of the main challenges to extracting data from images of tables is accurately recognizing table structures, especially for complex tables with cross rows and columns.In this study, we propose a novel multi-modal pre-training model for table structure recognition, named TableVLM.With a two-stream multi-modal transformer-based encoder-decoder architecture, TableVLM learns to capture rich table structure-related features by multiple carefully-designed unsupervised objectives inspired by the notion of masked visual-language modeling.To pre-train this model, we also created a dataset, called ComplexTable, which consists of 1,000K samples to be released publicly. Experiment results show that the model built on pre-trained TableVLM can improve the performance up to 1.97% in tree-editing-distance-score on ComplexTable.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/65b75329-48fd-4881-988b-9355c6cf9c8b" width="300" height="400"></iframe>

TableVLM: Multi-modal Pre-training for Table Structure Recognition

The inevitable private information in legal data necessitates legal artificial intelligence to study privacy-preserving and decentralized learning methods. Federated learning (FL) has merged as a promising technique for multiple participants to collaboratively train a shared model while efficiently protecting the sensitive data of participants. However, to the best of our knowledge, there is no work on applying FL to legal NLP. To fill this gap, this paper presents the first real-world FL benchmark for legal NLP, coined FEDLEGAL, which comprises five legal NLP tasks and one privacy task based on the data from Chinese courts. Based on the extensive experiments on these datasets, our results show that FL faces new challenges in terms of real-world non-IID data. The benchmark also encourages researchers to investigate privacy protection using real-world data in the FL setting, as well as deploying models in resource-constrained scenarios. The code and datasets of FEDLEGAL are available here.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/5e454aa7-3b79-4ed0-95e9-76a35a1ae5dd" width="300" height="400"></iframe>

FEDLEGAL: The First Real-World Federated Learning Benchmark for Legal NLP

Named entity recognition in real-world applications suffers from the diversity of entity types, the emergence of new entity types, and the lack of high-quality annotations. To address the above problems, this paper proposes an in-context learning-based NER approach, which can effectively inject in-context NER ability into PLMs and recognize entities of novel types on-the-fly using only a few demonstrative instances. Specifically, we model PLMs as a meta-function Lambda_{instruction, demonstrations, text}.M, and a new entity extractor can be implicitly constructed by applying new instruction and demonstrations to PLMs, i.e., (Lambda . M) }(instruction, demonstrations) ->F where F will be a new entity extractor F: text -> entities. To inject the above in-context NER ability into PLMs, we propose a meta-function pre-training algorithm, which pre-trains PLMs by comparing the (instruction, demonstration)-initialized extractor with a surrogate golden extractor. Experimental results on 4 few-shot NER datasets show that our method can effectively inject in-context NER ability into PLMs and significantly outperforms the PLMs+fine-tuning counterparts.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/c80063e8-cb65-428f-8aee-3de518f91411" width="300" height="400"></iframe>

Learning In-context Learning for Named Entity Recognition

Training grounded response generation models often requires a large collection of grounded dialogues. However, it is costly to build such dialogues. In this paper, we present a synthetic data generation framework (SynDG) for grounded dialogues. The generation process utilizes large pre-trained language models and freely available knowledge data (e.g., Wikipedia pages, persona profiles, etc.). The key idea of designing SynDG is to consider dialogue flow and coherence in the generation process. Specifically, given knowledge data, we first heuristically determine a dialogue flow, which is a series of knowledge pieces. Then, we employ T5 to incrementally turn the dialogue flow into a dialogue. To ensure coherence of both the dialogue flow and the synthetic dialogue, we design a two-level filtering strategy, at the flow-level and the utterance-level respectively. Experiments on two public benchmarks show that the synthetic grounded dialogue data produced by our framework is able to significantly boost model performance in both full training data and low-resource scenarios.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/e43bcc16-6f3a-406a-b8ab-709e36c2c004" width="300" height="400"></iframe>

A Synthetic Data Generation Framework for Grounded Dialogues

Demographic biases and social stereotypes are common in pretrained language models (PLMs), and a burgeoning body of literature focuses on removing the unwanted stereotypical associations from PLMs. However, when fine-tuning these bias-mitigated PLMs in downstream natural language processing (NLP) applications, such as sentiment classification, the unwanted stereotypical associations resurface or even get amplified. Since pretrain&fine-tune is a major paradigm in NLP applications, separating the debiasing procedure of PLMs from fine-tuning would eventually harm the actual downstream utility. In this paper, we propose a unified debiasing framework Causal-Debias to remove unwanted stereotypical associations in PLMs during fine-tuning. Specifically, CausalDebias mitigates bias from a causal invariant perspective by leveraging the specific downstream task to identify bias-relevant and labelrelevant factors. We propose that bias-relevant factors are non-causal as they should have little impact on downstream tasks, while labelrelevant factors are causal. We perform interventions on non-causal factors in different demographic groups and design an invariant risk minimization loss to mitigate bias while maintaining task performance. Experimental results on three downstream tasks show that our proposed method can remarkably reduce unwanted stereotypical associations after PLMs are finetuned, while simultaneously minimizing the impact on PLMs and downstream applications.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/012a7aca-50e3-4ef6-80cf-c824f0c41ec0" width="300" height="400"></iframe>

Causal-Debias: Unifying Debiasing in Pretrained Language Models and Fine-tuning via Causal Invariant Learning

In this paper, we propose a table and image generation task to verify how the knowledge about entities acquired from natural language is retained in Vision & Language (V & L) models. This task consists of two parts: the first is to generate a table containing knowledge about an entity and its related image, and the second is to generate an image from an entity with a caption and a table containing related knowledge of the entity. In both tasks, the model must know the entities used to perform the generation properly. We created the Wikipedia Table and Image Generation (WikiTIG) dataset from about 200,000 infoboxes in English Wikipedia articles to perform the proposed tasks. We evaluated the performance on the tasks with respect to the above research question using the V & L model OFA, which has achieved state-of-the-art results in multiple tasks. Experimental results show that OFA forgets part of its entity knowledge by pre-training as a complement to improve the performance of image related tasks.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/7c16a6c5-ee36-4c9f-9ed1-481b0d0ef00a" width="300" height="400"></iframe>

Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language Models

Prior works on joint Information Extraction (IE) typically model instance (e.g., event triggers, entities, roles, relations) interactions by representation enhancement, type dependencies scoring, or global decoding. We find that the previous models generally consider binary type dependency scoring of a pair of instances, and leverage local search such as beam search to approximate global solutions. To better integrate cross-instance interactions, in this work, we introduce a joint IE framework (CRFIE) that formulates joint IE as a high-order Conditional Random Field. Specifically, we design binary factors and ternary factors to directly model interactions between not only a pair of instances but also triplets. Then, these factors are utilized to jointly predict labels of all instances.To address the intractability problem of exact high-order inference, we incorporate a high-order neural decoder that is unfolded from a mean-field variational inference method, which achieves consistent learning and inference. The experimental results show that our approach achieves consistent improvements on three IE tasks compared with our baseline and prior work.\footnote{The code and trained models can be found at \url{https://github.com/Anonymous}.}

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/372f6881-2e2e-47fc-835e-f0fb6d13ad47" width="300" height="400"></iframe>

Modeling Instance Interactions for Joint Information Extraction with Neural High-Order Conditional Random Field

Dialogue models are often enriched with extensive external knowledge to provide informative responses through a retrieval-augmented pipeline.Nevertheless, retrieval-augmented approaches rely on finely annotated retrieval training data and knowledge-grounded response generation data, making it costly to transfer. To tackle this challenge, this paper proposed a retrieval-free approach, KiDG, by automatically turning knowledge documents into simulated multi-turn dialogues through a Multi-Document Traversal algorithm. The simulated knowledge-intensive dialogues constructed by KiDG in one domain can be easily used to train and enhance pre-trained dialogue models' knowledge w.r.t. this domain without costly annotation.We conduct extensive experiments comparing retrieval-augmented models and a variety of retrieval-free models. We found that dialogue models enhanced with data simulated with KiDG largely outperform state-of-the-art retrieval-free methods, and it achieves comparable performance compared to retrieval-augmented methods while being better, and cheaper at domain transfer.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/635fccb2-37c1-40b2-94f5-1dba2e75bd9c" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control

Similar lecture

Ranking Unraveled: Recipes for LLM Rankings in Head-to-Head AI Combat