United States

Large language models (LLMs) are essential tools that users employ across various scenarios, so evaluating their performance and guiding users in selecting the suitable service is important. Although many benchmarks exist, they mainly focus on specific predefined model abilities, such as world knowledge, reasoning, etc. Based on these ability scores, it is hard for users to determine which LLM best suits their particular needs. To address these issues, we propose to evaluate LLMs from a user-centric perspective and design this benchmark to measure their efficacy in satisfying user needs under distinct intents. Firstly, we collect 1,846 real-world use cases from a user study with 712 participants from 23 countries. This first-hand data helps us understand actual user intents and needs in LLM interactions, forming the User Reported Scenarios (URS) dataset, which is categorized with six types of user intents. Secondly, based on this authentic dataset, we benchmark 10 LLM services with GPT-4-as-Judge. Thirdly, we show that benchmark scores align well with human preference in both real-world experience and pair-wise annotations, achieving Pearson correlations of 0.95 and 0.94, respectively. This alignment confirms that the URS dataset and our evaluation method establish an effective user-centric benchmark. The dataset, code, and process data are publicly available at https://github.com/Alice1998/URS.

EMNLP 2024

A User-Centric Multi-Intent Benchmark for Evaluating Large Language Models

evaluation methodologies

vision question answering

interpretability

### Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

NAACL 2025

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

technical paper

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

When large language models are aligned via supervised fine-tuning, they may encounter new factual information that was not acquired through pre-training. It is often conjectured that this can teach the model the behavior of hallucinating factually incorrect responses, as the model is trained to generate facts that are not grounded in its pre-existing knowledge. In this work, we study the impact of such exposure to new knowledge on the capability of the fine-tuned model to utilize its pre-existing knowledge. To this end, we design a controlled setup, focused on closed-book QA, where we vary the proportion of the fine-tuning examples that introduce new knowledge. We demonstrate that large language models struggle to acquire new factual knowledge through fine-tuning, as fine-tuning examples that introduce new knowledge are learned significantly slower than those consistent with the model's knowledge. However, we also find that as the examples with new knowledge are eventually learned, they linearly increase the model's tendency to hallucinate. Taken together, our results highlight the risk in introducing new factual knowledge through fine-tuning, and support the view that large language models mostly acquire factual knowledge through pre-training, whereas fine-tuning teaches them to use it more efficiently.

Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?

The deployment of large language models (LLMs) is often hindered by the extensive memory requirements of the Key-Value (KV) cache, especially as context lengths increase. Existing approaches to reduce the KV cache size involve either fine-tuning the model to learn a compression strategy or leveraging attention scores to reduce the sequence length. We analyse the attention distributions in decoder-only Transformers-based models and observe that attention allocation patterns stay consistent across most layers. Surprisingly, we find a clear correlation between the $L_2$ norm and the attention scores over cached KV pairs, where a low $L_2$ norm of a key embedding usually leads to a high attention score during decoding. This finding indicates that the influence of a KV pair is potentially determined by the key embedding itself before being queried. Based on this observation, we compress the KV cache based on the $L_2$ norm of key embeddings. Our experimental results show that this simple strategy can reduce the KV cache size by 50% on language modelling and needle-in-a-haystack tasks and 90% on passkey retrieval tasks without losing accuracy. Moreover, without relying on the attention scores, this approach remains compatible with FlashAttention, enabling broader applicability.

A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression

Existing works show that augmenting the training data of pre-trained language models (PLMs) for classification tasks fine-tuned via parameter-efficient fine-tuning methods (PEFT) using both clean and adversarial examples can enhance their robustness under adversarial attacks. However, this adversarial training paradigm often leads to performance degradation on clean inputs and requires frequent re-training on the entire data to account for new, unknown attacks. To overcome these challenges while still harnessing the benefits of adversarial training and the efficiency of PEFT, this work proposes a novel approach, called AdpMixup, that combines two paradigms: (1) fine-tuning through adapters and (2) adversarial augmentation via mixup to dynamically leverage existing knowledge from a set of pre-known attacks for robust inference. Intuitively, AdpMixup fine-tunes PLMs with multiple adapters with both clean and pre-known adversarial examples and intelligently mixes them up in different ratios during prediction. Our experiments show AdpMixup achieves the best trade-off between training efficiency and robustness under both pre-known and unknown attacks, compared to existing baselines on five downstream tasks across six varied black-box attacks and 2 PLMs. The code is available at https://github.com/nguyentuc/adapters_mixup.

Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers

Large Language Models (LLMs) are increasingly integrated into diverse applications. The rapid evolution of LLMs presents opportunities for developers to enhance applications continuously. However, this constant adaptation can also lead to performance regressions during model migrations. While several interactive tools have been proposed to streamline the complexity of prompt engineering, few address the specific requirements of regression testing for LLM Migrations. To bridge this gap, we introduce RETAIN (REgression Testing guided LLM migrAtIoN), a tool designed explicitly for regression testing in LLM Migrations. RETAIN comprises two key components: an interactive interface tailored to regression testing needs during LLM migrations, and an error discovery module that facilitates understanding of differences in model behaviors. The error discovery module generates textual descriptions of various errors or differences between model outputs, providing actionable insights for prompt refinement. Our automatic evaluation and empirical user studies demonstrate that RETAIN, when compared to manual evaluation, enabled participants to identify twice as many errors, facilitated experimentation with 75\% more prompts, and achieves 12\% higher metric scores in a given time frame.

RETAIN: Interactive Tool for Regression Testing Guided LLM Migration

The widespread accessibility of large language models (LLMs) to the general public has significantly amplified the dissemination of machine-generated texts (MGTs). Advancements in prompt manipulation have exacerbated the difficulty in discerning the origin of a text (human-authored vs machinegenerated). This raises concerns regarding the potential misuse of MGTs, particularly within educational and academic domains. In this paper, we present $\textbf{LLM-DetectAIve}$ -- a system designed for fine-grained MGT detection. It is able to classify texts into four categories: human-written, machine-generated, machine-written machine-humanized, and human-written machine-polished. Contrary to previous MGT detectors that perform binary classification, introducing two additional categories in LLM-DetectiAIve offers insights into the varying degrees of LLM intervention during the text creation. This might be useful in some domains like education, where any LLM intervention is usually prohibited. Experiments show that LLM-DetectAIve can effectively identify the authorship of textual content, proving its usefulness in enhancing integrity in education, academia, and other domains. LLM-DetectAIve is publicly accessible at https://huggingface.co/spaces/raj-tomar001/MGT-New. The video describing our system is available at https://youtu.be/E8eT_bE7k8c.

LLM-DetectAIve: a Tool for Fine-Grained Machine-Generated Text Detection

Generative models have demonstrated considerable potential in software engineering, particularly in tasks such as code generation and debugging. However, their utilization in the domain of code documentation generation remains underexplored. To this end, we introduce RepoAgent, a large language model powered open-source framework aimed at proactively generating, maintaining, and updating code documentation. Through both qualitative and quantitative evaluations, we have validated the effectiveness of our approach, showing that RepoAgent excels in generating high-quality repository-level documentation. The code and results are publicly accessible at https://github.com/OpenBMB/RepoAgent.

RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation

Despite the longstanding adage ''an image is worth a thousand words,'' generating accurate hyper-detailed image descriptions remains unsolved. Trained on short web-scraped image-text, vision-language models often generate incomplete descriptions with visual inconsistencies. We address this via a novel data-centric approach with ImageInWords (IIW), a carefully designed human-in-the-loop framework for curating hyper-detailed image descriptions. Human evaluations on IIW data show major gains compared to recent datasets (+66%) and GPT-4V (+48%) across comprehensiveness, specificity, hallucinations, and more. We also show that fine-tuning with IIW data improves these metrics by +31% against models trained with prior work, even with only 9k samples. Lastly, we evaluate IIW models with text-to-image generation and vision-language reasoning tasks. Our generated descriptions result in the highest fidelity images, and boost compositional reasoning by up to 6% on ARO, SVO-Probes, and Winoground datasets. We release the IIW-Eval benchmark with human judgement labels, object and image-level annotations from our framework, and existing image caption datasets enriched via IIW-model.

ImageInWords: Unlocking Hyper-Detailed Image Descriptions

Depression is a critical concern in global mental health, prompting extensive research into AI-based detection methods. Among various AI technologies, Large Language Models (LLMs) stand out for their versatility in healthcare applications. However, the application of LLMs in the identification and analysis of depressive states remains relatively unexplored, presenting an intriguing avenue for future research. In this paper, we present an innovative approach to employ an LLM in the realm of depression detection, integrating acoustic speech information into the LLM framework for this specific application. We investigate an efficient method for automatic depression detection by integrating speech signals into LLMs utilizing Acoustic Landmarks. This approach is not only valuable for the detection of depression but also represents a new perspective in enhancing the ability of LLMs to comprehend and process speech signals. By incorporating acoustic landmarks, which are specific to the pronunciation of spoken words, our method adds critical dimensions to text transcripts. This integration also provides insights into the unique speech patterns of individuals, revealing the potential mental states of individuals. By encoding acoustic landmarks information into LLMs, evaluations of the proposed approach on the DAIC-WOZ dataset reveal state-of-the-art results when compared with existing Audio-Text baselines.

When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection

Embedding models play a pivotal role in modern NLP applications such as document retrieval. However, existing embedding models are limited to encoding short documents of typically 512 tokens, restrained from application scenarios requiring long inputs. This paper explores context window extension of existing embedding models, pushing their input length to a maximum of 32,768. We begin by evaluating the performance of existing embedding models using our newly constructed LongEmbed benchmark, which includes two synthetic and four real-world tasks, featuring documents of varying lengths and dispersed target information. The benchmarking results highlight huge opportunities for enhancement in current models. Via comprehensive experiments, we demonstrate that training-free context window extension strategies can effectively increase the input length of these models by several folds. Moreover, comparison of models using Absolute Position Encoding (APE) and Rotary Position Encoding (RoPE) reveals the superiority of RoPE-based embedding models in context window extension, offering empirical guidance for future models. Our benchmark, code and trained models will be released to advance the research in long context embedding models.

LongEmbed: Extending Embedding Models for Long Context Retrieval

Retrieval-augmented Large Language Models (LLMs) offer substantial benefits in enhancing performance across knowledge-intensive scenarios. However, these methods often struggle with complex inputs and encounter difficulties due to noisy knowledge retrieval, notably hindering model effectiveness. To address this issue, we introduce BlendFilter, a novel approach that elevates retrieval-augmented LLMs by integrating query generation blending with knowledge filtering. BlendFilter proposes the blending process through its query generation method, which integrates both external and internal knowledge augmentation with the original query, ensuring comprehensive information gathering. Additionally, our distinctive knowledge filtering module capitalizes on the intrinsic capabilities of the LLM, effectively eliminating extraneous data. We conduct extensive experiments on three open-domain question answering benchmarks, and the findings clearly indicate that our innovative BlendFilter surpasses state-of-the-art baselines significantly.

Downloads

Next from EMNLP 2024

Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?

Similar lecture

UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models