Malta

Large Language Models (LLMs) have shown promising performance in summary evaluation tasks, yet they face challenges such as high computational costs and the \textit{Lost-in-the-Middle} problem where important information in the middle of long documents is often overlooked. To address these issues, this paper introduces a novel approach, Extract-then-Evaluate, which involves extracting key sentences from a long source document and then evaluating the summary by prompting LLMs. The results reveal that the proposed method not only significantly reduces evaluation costs but also exhibits a higher correlation with human evaluations. Furthermore, we provide practical recommendations for optimal document length and sentence extraction methods, contributing to the development of cost-effective yet more accurate methods for LLM-based text generation evaluation.

EACL 2024

Less is More for Long Document Summary Evaluation by LLMs

text generation evaluation

summarization

technical paper

Welcome to the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Continuing its mission of expanding and involving the science community of all European countries, EACL has selected the Malta community for the 18th EACL. Considering the importance of physical interaction among researchers, the conference will be held at the Hotel Radisson Blu, St. Julians, in Malta, from 17 to 22 of March, 2024. The conference will also feature the possibility to participate virtually. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language. 
#### [Conference Handbook](https://drive.google.com/file/d/13Wn38q0yev6U3RTgnf4Tn5T9GuAuZ-xW/view?usp=sharing) *downloadable*

To access the EACL 2024 event page you need to register [**here**](https://acl.swoogo.com/EACL2024). 

Please register!

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

An increasing amount of research in Natural Language Inference (NLI) focuses on the application and evaluation of Large Language Models (LLMs) and their reasoning capabilities. Despite their success, however, LLMs are still prone to factual errors and inconsistencies in their explanations, offering limited control and interpretability for inference in complex domains. 
In this paper, we focus on ethical NLI, investigating how hybrid neuro-symbolic techniques can enhance the logical validity and alignment of ethical explanations produced by LLMs. Specifically, we present an abductive-deductive framework named Logic-Explainer, which integrates LLMs with an external backward-chaining solver to refine step-wise natural language explanations and jointly verify their correctness, reduce incompleteness and minimise redundancy. An extensive empirical analysis demonstrates that Logic-Explainer can improve explanations generated via in-context learning methods and Chain-of-Thought (CoT) on challenging ethical NLI tasks, while, at the same time, producing formal proofs describing and supporting models' reasoning. As ethical NLI requires commonsense reasoning to identify underlying moral violations, our results suggest the effectiveness of neuro-symbolic methods for multi-step NLI more broadly, opening new opportunities to enhance the logical consistency, reliability, and alignment of LLMs.

Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement

Hallucinations and off-target translation remain unsolved problems in MT, especially for low-resource languages and massively multilingual models. In this paper, we introduce two related methods to mitigate these failure cases with a modified decoding objective, without either requiring retraining or external models. In source-contrastive decoding, we search for a translation that is probable given the correct input, but improbable given a random input segment. In language-contrastive decoding, we search for a translation that is probable, but improbable given the wrong language indicator token. Experiments on the massively multilingual models M2M-100 (418M) and SMaLL-100 show that these methods suppress hallucinations and off-target translations, reducing the number of translations with segment-level chrF2 below 10 by 67-83% on average across 57 tested translation directions. In a proof of concept on out-of-English translation, we also show that we can suppress off-target translations with large language models. We release code upon acceptance.

Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding

Despite the revolution caused by deep NLP models, they remain black boxes, necessitating research to understand their decision-making processes. A recent work by Dalvi et al. (2022) carried out representation analysis through the lens of clustering latent spaces within pre-trained models (PLMs), but that approach is limited to small scale due to the high cost of running Agglomerative hierarchical clustering. This paper studies clustering algorithms in order to scale the discovery of encoded concepts in PLM representations to larger datasets and models. We propose metrics for assessing the quality of discovered latent concepts and use them to compare the studied clustering algorithms. We found that K-Means-based concept discovery significantly enhances efficiency while maintaining the quality of the obtained concepts. Furthermore, we demonstrate the practicality of this newfound efficiency by scaling latent concept discovery to LLMs and phrasal concepts.

Scaling up Discovery of Latent Concepts in Deep NLP Models

This paper introduces a novel decision-making framework that promotes consistency among decisions made by diverse models while utilizing external knowledge. Leveraging the Integer Linear Programming(ILP) framework, we map predictions from various models into globally normalized and comparable values by incorporating information about decisions' prior probability, confidence~(uncertainty), and the models' expected accuracy. Our empirical study demonstrates the superiority of our approach over conventional baselines on multiple datasets.

Consistent Joint Decision-Making with Heterogeneous Learning Models

There has been a range of studies of how autism is displayed in voice, speech, and language. We analyse studies from the biomedical, as well as the psychological domain, but also from the NLP domain in order to find linguistic, prosodic and acoustic cues. Our survey looks at all three domains. We define autism and which comorbidities might influence the correct detection of the disorder. We especially look at observations such as verbal and semantic fluency, prosodic features, but also disfluencies and speaking rate. We also show word-based approaches and describe machine learning and transformer-based approaches both on the audio data as well as the transcripts. Lastly, we conclude, while there already is a lot of research, female patients seem to be severely under-researched. 
Also, most NLP research focuses on traditional machine learning methods instead of transformers. Additionally, we were unable to find research combining both features from audio and transcripts.

Autism Detection in Speech – A Survey

Backward compatibility of model predictions is a desired property when updating a machine learning driven application. It allows to seamlessly improve the underlying model without introducing regression bugs. In classification tasks these bugs occur in the form of negative flips. This means an instance that was correctly classified by the old model is now classified incorrectly by the updated model. This has direct negative impact on the user experience of such systems e.g. a frequently used voice assistant query is suddenly misclassified.
A common reason to update the model is when new training data becomes available and needs to be incorporated. Simply retraining the model with the updated data introduces the unwanted negative flips. We study the problem of regression during data updates and propose Backward Compatible Weight Interpolation (BCWI). This method interpolates between the weights of the old and new model and we show in extensive experiments that it reduces negative flips without sacrificing the improved accuracy of the new model. BCWI is straight forward to implement and does not increase inference cost. We also explore the use of importance weighting during interpolation and averaging the weights of multiple new models in order to further reduce negative flips.

Backward Compatibility During Data Updates by Weight Interpolation

The statistical analysis of large scale legal corpus can provide valuable legal insights. For such analysis one needs to (1) select a subset of the corpus using document retrieval tools, (2) structure text using information extraction (IE) systems, and (3) visualize the data for the statistical analysis. Each process demands either specialized tools or programming skills whereas no comprehensive unified “no-code” tools have been available. Here we provide N ESTLE, a no-code tool for large-scale statistical analysis of legal corpus. Powered by a Large Language Model (LLM) and the internal custom end-to-end IE system, N ESTLE can extract any type of information that has not been predefined in the IE system opening up the possibility of unlimited customizable statistical analysis of the corpus without writing a single line of code. We validate our system on 15 Korean precedent IE tasks and 3 legal text classification tasks from L EX GLUE. The comprehensive experiments reveal N ESTLE can achieve GPT-4 comparable performance by training the internal IE module with 4 human-labeled, and 192 LLM-labeled examples.

NESTLE: a No-Code Tool for Statistical Analysis of Legal Corpus

Spatial information in text enables to understand the geographical context and relationships within text for better decision-making across various domains such as disease surveillance, disaster management and other location-based services. Therefore, it is crucial to understand the precise geographical context for location-sensitive applications. In response to this necessity, we introduce the GeospaCy software tool, designed for the extraction and georeferencing of spatial information present in textual data. GeospaCy fulfils two primary objectives: 1) Geoparsing, which involves extracting spatial expressions, encompassing place names and associated spatial relations within the text data, and 2) Geocoding, which facilitates the assignment of geographical coordinates to the spatial expressions extracted during the Geoparsing task. Geoparsing is evaluated with a disease news article dataset consisting of event information, whereas a qualitative evaluation of geographical coordinates (polygons/geometries) of spatial expressions is performed by end-users for Geocoding task.

GeospaCy: A tool for extraction and geographical referencing of spatial expressions in textual data

Large language models (LLMs) can label data faster and cheaper than humans for various NLP tasks. Despite their prowess, LLMs may fall short in understanding of complex, sociocultural, or domain-specific context, potentially leading to incorrect annotations. Therefore, we advocate a collaborative approach where humans and LLMs work together to produce reliable and high-quality labels. We present MEGAnno+, a human-LLM collaborative annotation system that offers effective LLM agent and annotation management, convenient and robust LLM annotation, and exploratory verification of LLM labels by humans.

MEGAnno+: A Human-LLM Collaborative Annotation System

Automatic text simplification (TS) aims to automate the process of rewriting text to make it easier for people to read. A prerequisite for TS to be useful is that it should convey information that is consistent with the meaning of the original text. However, current TS evaluation protocols assess system outputs for simplicity and meaning preservation without regard for the document context in which output sentences occur and for how people understand them. In this work, we introduce a human evaluation framework to assess whether simplified texts preserve meaning using reading comprehension questions. With this framework, we conduct a thorough human evaluation of texts by humans and by nine automatic systems. Supervised systems that leverage pre-training knowledge achieve the highest scores on the reading comprehension (RC) tasks amongst the automatic controllable TS systems. However, even the best-performing supervised system struggles with at least 14% of the questions, marking them as "unanswerable'' based on simplified content. We further investigate how existing TS evaluation metrics and automatic question-answering systems approximate the human judgments we obtained.

Premium content

Less is More for Long Document Summary Evaluation by LLMs

Downloads

Next from EACL 2024

Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES