Thailand

In-context learning (ICL) has emerged as a powerful tool for enhancing large language models (LLMs) in addressing downstream tasks. In this paper, we explore the vital task of example selection in ICL by mimicking the human learning process. We propose a Chain-of-Quizzes (CoQ) framework inspired by educational theories such as Bruner&#39;s Spiral Learning and Mastery Learning theory. Specifically, our framework employs the LLMs to answer the quiz (question in the example) to sift `good&#39; examples, combines these examples iteratively with the increasing complexity, and utilizes a final exam to gauge the combined example chains. Our extensive experiments on diverse reasoning datasets show the proposed approach outperforms baseline models. These findings underscore the framework&#39;s potential for future research.

ACL 2024

Chain-of-Quizzes: Pedagogy-inspired Example Selection in In-Context-Learning

example selection

in context learning

large language model

### 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)

In-context learning (ICL) has emerged as a powerful tool for enhancing large language models (LLMs) in addressing downstream tasks. In this paper, we explore the vital task of example selection in ICL by mimicking the human learning process. We propose a Chain-of-Quizzes (CoQ) framework inspired by educational theories such as Bruner's Spiral Learning and Mastery Learning theory. Specifically, our framework employs the LLMs to answer the quiz (question in the example) to sift `good' examples, combines these examples iteratively with the increasing complexity, and utilizes a final exam to gauge the combined example chains. Our extensive experiments on diverse reasoning datasets show the proposed approach outperforms baseline models. These findings underscore the framework's potential for future research.

poster

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

Intent detection aims to identify user goals from utterances, and is a ubiquitous step towards the satisfaction of user desired needs in many interaction systems. As dynamic and varied intents arise, models that are capable of identifying new intents promptly are required. However, existing studies usually fine-tune discriminative models on the specific defined intent classes, precluding them from being directly adopted to new intent domains. In this paper, we introduce a generative pre-trained intent model that can recognize new intents from different domains in low-resource scenarios. We reformulate intent detection into a generation task and design descriptive and regularized instructions to guide the model effectively to detect new intents in open domains with no parameter updates. To validate the proposed method, we introduce a new intent detection benchmark, including the Meta-Intent Dataset and three types of representative evaluation settings. We conduct extensive experiments which demonstrate that our method outperforms a range of strong baselines that needs further fine-tuning or domain-specific samples.

From Discrimination to Generation: Low-Resource Intent Detection with Language Model Instruction Tuning

Instruction tuning has been used as a promising approach to improve the performance of large language models (LLMs) on unseen tasks. However, current LLMs exhibit limited robustness to unseen instructions, generating inconsistent outputs when the same instruction is phrased with slightly varied forms or language styles. This behavior indicates LLMs' lack of robustness to textual variations and generalizability to unseen instructions, potentially leading to trustworthiness issues. Accordingly, we propose Contrastive Instruction Tuning, which maximizes the similarity between the hidden representations of semantically equivalent instruction-instance pairs while minimizing the similarity between semantically different ones. To facilitate this approach, we augment the existing FLAN collection by paraphrasing task instructions. Experiments on the PromptBench benchmark show that CoIN consistently improves LLMs' robustness to unseen instructions with variations across character, word, sentence, and semantic levels by an average of +2.5% in accuracy.

Contrastive Instruction Tuning

Making inferences in text comprehension to understand the meaning is essential in language processing. This work studies the entailment verification (EV) problem of complex, multi-sentence premises requiring a system to make multiple inferences implicitly. Modern applications of EV in detecting inconsistent model-generated rationales require complex multi-hop reasoning. However, current textual inference datasets mostly contain short-sentence premises that partially focus on this. To address this, we compile an EV benchmark that includes datasets from three NLP domains (NLI, contextual QA, and rationales) containing multi-sentence premises. On benchmarking humans and LLMs, we find that LLMs are better than humans in multi-hop reasoning across extended contexts, while humans perform better in simple deductive reasoning tasks. We also finetune a Flan-T5 model for EV using two training objectives to obtain a strong open-source model that outperforms GPT-3.5 and rivals GPT-4. Finally, we use our finetuned model to filter out inconsistent model-generated rationales in self-consistency decoding, resulting in a 6% accuracy improvement on average across three MCQ datasets.

Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification

Weight-sharing supernets are crucial for performance estimation in cutting-edge neural architecture search (NAS) frameworks. Despite their ability to generate diverse subnetworks without retraining, the quality of these subnetworks is not guaranteed due to weight sharing. In NLP tasks like machine translation and pre-trained language modeling, there is a significant performance gap between supernet and training from scratch for the same model architecture, necessitating retraining post optimal architecture identification.

This study introduces a solution called mixture-of-supernets, a generalized supernet formulation leveraging mixture-of-experts (MoE) to enhance supernet model expressiveness with minimal training overhead. Unlike conventional supernets, this method employs an architecture-based routing mechanism, enabling indirect sharing of model weights among subnetworks. This customization of weights for specific architectures, learned through gradient descent, minimizes retraining time, significantly enhancing training efficiency in NLP. The proposed method attains state-of-the-art (SoTA) performance in NAS for fast machine translation models, exhibiting a superior latency-BLEU tradeoff compared to HAT, the SoTA NAS framework for machine translation. Furthermore, it excels in NAS for building memory-efficient task-agnostic BERT models, surpassing NAS-BERT and AutoDistil across various model sizes. The code can be found at: https://github.com/UBC-NLP/MoS.

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts

Visually-rich document information extraction (VIE) is a vital aspect of document understanding, wherein Semantic Entity Recognition (SER) plays a significant role. However, few-shot SER on visually-rich documents remains relatively unexplored despite its considerable potential for practical applications. To address this issue, we propose a simple yet effective Plug-and-Play Tag-guided method for few-shot Semantic Entity Recognition (PPTSER) on visually-rich documents. PPTSER is built upon off-the-shelf multi-modal pre-trained models. It leverages the semantics of the tags to guide the SER task, reformulating SER into entity typing and span detection, handling both tasks simultaneously via cross-attention. Experimental results illustrate that PPTSER outperforms existing fine-tuning and few-shot methods, especially in low-data regimes. With full training data, PPTSER achieves comparable or superior performance to fine-tuning baseline. For instance, on the FUNSD benchmark, our method improves the performance of LayoutLMv3-base in 1-shot, 3-shot and 5-shot scenarios by 15.61%, 2.13%, and 2.01%, respectively. Overall, PPTSER demonstrates promising generalizability, effectiveness, and plug-and-play nature for few-shot SER on visually-rich documents. The codes will be available at [https://github.com/whlscut/PPTSER](https://github.com/whlscut/PPTSER).

PPTSER: A Plug-and-Play Tag-guided Method for Few-shot Semantic Entity Recognition on Visually-rich Documents

To reliably deploy Large Language Models (LLMs) in a specific country, they must possess an understanding of the nation's culture and basic knowledge. To this end, we introduce National Alignment, which measures the alignment between an LLM and a targeted country from two aspects: social value alignment and common knowledge alignment. We constructed KorNAT, the first benchmark that measures national alignment between LLMs and South Korea. KorNat contains 4K and 6K multiple-choice questions for social value and common knowledge, respectively. To attain an appropriately aligned ground truth in the social value dataset, we conducted a large-scale public survey with 6,174 South Koreans. For common knowledge, we created the data based on the South Korea text books and GED exams. Our dataset creation process is meticulously designed based on statistical sampling theory, and we also introduce metrics to measure national alignment, including three variations of social value alignment. We tested seven LLMs and found that only few models passed our reference score, indicating there exists room for improvement. Our dataset has received government approval following an assessment by a government-affiliated organization dedicated to evaluating dataset quality.

KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge

NLU models have achieved promising results on standard benchmarks. Despite state-of-the-art accuracy, analysis reveals that many models make predictions using annotation bias rather than the properties we intend the model to learn. Consequently, these models perform poorly on out-of-distribution datasets. Recent advances in bias mitigation show that annotation bias can be alleviated through fine-tuning debiasing objectives. In this paper, we apply causal mediation analysis to gauge how much each model component mediates annotation biases. Using the knowledge from the causal analysis, we improve the model's robustness against annotation bias through two bias mitigation methods: causal-grounded masking and gradient unlearning. Causal analysis reveals that biases concentrated in specific components, even after employing other training-time debiasing techniques. Manipulating these components by masking out neurons' activations or updating specific weight blocks both demonstrably improve robustness against annotation artifacts.

Identifying and Mitigating Annotation Bias in Natural Language Understanding using Causal Mediation Analysis

Question answering over temporal knowledge graphs (TKGQA) is an emerging topic, which has attracted increasing interest since it considers the dynamic knowledge in the world. Several datasets along with model developments are proposed in the TKGQA research field. However, existing studies generally focus on fact-centered reasoning, with limited attention to temporal reasoning. To tackle the intricate and comprehensive nature of temporal reasoning, we propose a new TKGQA dataset, MusTQ, which contains 666K multi-step temporal reasoning questions as well as a TKG. The multi-step temporal reasoning is established based on six basic temporal reasoning types derived from a well-established measure theory. Using MusTQ, we evaluate previous TKGQA methods and find that they typically fall short in multi-step temporal reasoning. Furthermore, we propose a TKGQA model, MusTKGQA, which enhances multi-step reasoning ability with entity-time attention mechanism and optimized temporal knowledge graph representation. Extensive experiments on MusTQ show that our model achieves state-of-the-art multi-step temporal reasoning performance.

MusTQ: A Temporal Knowledge Graph Question Answering Dataset for Multi-Step Temporal Reasoning

Fine-tuning pre-trained language models, particularly large language models, demands extensive computing resources and can result in varying performance outcomes across different domains and datasets. This paper examines the approach of integrating multiple models from diverse training scenarios into a unified model. This unified model excels across various data domains and exhibits the ability to generalize well on out-of-domain data. We propose a knowledge fusion method named Evolver, inspired by evolutionary algorithms, which does not need further training or additional training data. Specifically, our method involves aggregating the weights of different language models into a population and subsequently generating offspring models through mutation and crossover operations. These offspring models are then evaluated against their parents, allowing for the preservation of those models that show enhanced performance on development datasets. Importantly, our model evolving strategy can be seamlessly integrated with existing model merging frameworks, offering a versatile tool for model enhancement. Experimental results on mainstream language models (i.e., encoder-only, decoder-only, encoder-decoder) reveal that Evolver outperforms previous state-of-the-art models by large margins.

Knowledge Fusion By Evolving Weights of Language Models

Multi-task learning (MTL) has shown considerable practical benefits, particularly when using language models (LMs). While this is commonly achieved by learning tasks under a joint optimization procedure, some methods, such as AdapterFusion, divide the problem into two stages: (i) task learning, where knowledge specific to a task is encapsulated within sets of parameters (e.g., adapters), and (ii) transfer, where this already learned knowledge is leveraged for a target task. This separation of concerns provides numerous benefits (e.g., promoting reusability). However, current two stage MTL introduces a substantial number of additional parameters. We address this issue by leveraging the usefulness of linearly scaling the output representations of source adapters for transfer learning. We introduce ScaLearn, a simple and highly parameter-efficient two-stage MTL method that capitalizes on the knowledge of the source tasks by learning a minimal set of scaling parameters that enable effective transfer to a target task. Our experiments on three benchmarks (GLUE, SuperGLUE, and HumSet) and two encoder LMs show that ScaLearn consistently outperforms strong baselines with a small number of transfer parameters ($\sim0.35$\% of those of AdapterFusion). Remarkably, we observe that ScaLearn maintains its strong abilities even when further reducing parameters, achieving competitive results with only 8 transfer parameters per target task. Our proposed approach thus demonstrates the power of simple scaling as a promise for more efficient task transfer. Our code is available at https://github.com/CPJKU/ScaLearn.

Downloads

Next from ACL 2024

From Discrimination to Generation: Low-Resource Intent Detection with Language Model Instruction Tuning

Similar lecture

Can Input Attributions Interpret the Inductive Reasoning Process in In-Context Learning?