United States

Foundation models (FMs) have achieved significant success across various tasks, leading to research on benchmarks for reasoning abilities. However, there is a lack of studies on FMs performance in exceptional scenarios, which we define as out-of-distribution (OOD) reasoning tasks. This paper is the first to address these cases, developing a novel dataset for evaluation of FMs across multiple modalities, including graphic novels, calligraphy, news articles, and lyrics. It includes tasks for instance classification, character recognition, token prediction, and text generation. The paper also proposes prompt engineering techniques like Chain-of-Thought (CoT) and CoT+Few-Shot to enhance performance. Validation of FMs using various methods revealed improvements. The code repository is accessible at: this https URL

EMNLP 2024

Benchmarking Foundation Models on Exceptional Cases: Dataset Creation and Validation

foundation models

out-of-distribution

multimodal

## 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.

Please register!

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.

Inferences from adjective-noun combinations like "Is artificial intelligence still intelligence?" provide a good test bed for LLMs' understanding of meaning and compositional generalization capability, since there are many combinations which are novel to both humans and LLMs but nevertheless elicit convergent human judgments. We study a range of LLMs and find that the largest models we tested are able to draw human-like inferences when the inference is determined by context and can generalize to unseen adjective-noun combinations. We also propose three methods to evaluate LLMs on these inferences out of context, where there is a distribution of human-like answers rather than a single correct answer. We find that LLMs show a human-like distribution on at most 75% of our dataset, which is promising but still leaves room for improvement.

Is artificial intelligence still intelligence? LLMs generalize to novel adjective-noun pairs, but don’t mimic the full human distribution

The evaluation of generative models in Machine Reading Comprehension (MRC) presents distinct difficulties, as traditional metrics like BLEU, ROUGE, METEOR, Exact Match, and F1 score often struggle to capture the nuanced and diverse responses. While embedding-based metrics such as BERTScore and BARTScore focus on semantic similarity, they still fail to fully address aspects such as recognizing additional helpful information and rewarding contextual faithfulness. Recent advances in large language model (LLM) based metrics offer more fine-grained evaluations, but challenges such as score clustering remain. This paper introduces a multi-aspect evaluation framework, CHIE, incorporating aspects of \textbf{C}orrectness, \textbf{H}elpfulness, \textbf{I}rrelevance, and \textbf{E}xtraneousness. Our approach, which uses binary categorical values rather than continuous rating scales, aligns well with human judgments, indicating its potential as a comprehensive and effective evaluation method.

CHIE: Generative MRC Evaluation for in-context QA with Correctness, Helpfulness, Irrelevancy, and Extraneousness Aspects

Existing research on Domain Robustness (DR) suffers from disparate setups, limited task variety, and scarce research on recent capabilities such as in-context learning. Furthermore, the common practice of measuring DR might not be fully accurate. Current research focuses on challenge sets and relies solely on the Source Drop (SD): Using the source in-domain performance as a reference point for degradation. However, we argue that the Target Drop (TD), which measures degradation from the target in-domain performance, should be used as a complementary point of view. To address these issues, we first curated a DR benchmark comprised of 7 diverse NLP tasks, which enabled us to measure both the SD and the TD. We then conducted a comprehensive large-scale DR study involving over 14,000 domain shifts across 21 fine-tuned models and few-shot LLMs. We found that both model types suffer from drops upon domain shifts. While fine-tuned models excel in-domain, few-shot LLMs often surpass them cross-domain, showing better robustness. In addition, we found that a large SD can often be explained by shifting to a harder domain rather than by a genuine DR challenge, and this highlights the importance of TD as a complementary metric. We hope our study will shed light on the current DR state of NLP models and promote improved evaluation practices toward more robust models.

Measuring the Robustness of NLP Models to Domain Shifts

This study investigates judgment prediction in a realistic scenario within the context of Indian judgments, utilizing a range of transformer-based models, including InLegalBERT, BERT, and XLNet, alongside LLMs such as Llama-2 and GPT-3.5 Turbo. In this realistic scenario, we simulate how judgments are predicted at the point when a case is presented for a decision in court, using only the information available at that time, such as the facts of the case, statutes, precedents, and arguments. This approach mimics real-world conditions, where decisions must be made without the benefit of hindsight, unlike retrospective analyses often found in previous studies. For transformer models, we experiment with hierarchical transformers and the summarization of judgment facts to optimize input for these models. Our experiments with LLMs reveal that GPT-3.5 Turbo excels in realistic scenarios, demonstrating robust performance in judgment prediction. Furthermore, incorporating additional legal information, such as statutes

Rethinking Legal Judgement Prediction in a Realistic Scenario in the Era of Large Language Models

This paper explores the intersection of technological innovation and access to justice by developing a benchmark for predicting case outcomes in the UK Employment Tribunal (UKET). To address the challenge of extensive manual annotation, the study employs a large language model (LLM) for automatic annotation, resulting in the creation of the CLC-UKET dataset. The dataset consists of approximately 19,000 UKET cases and their metadata. Comprehensive legal annotations cover facts, claims, precedent references, statutory references, case outcomes, reasons and jurisdiction codes. Facilitated by the CLC-UKET data, we examine a multi-class case outcome prediction task in the UKET. Human predictions are collected to establish a performance reference for model comparison. Empirical results from baseline models indicate that finetuned transformer models outperform zero-shot and few-shot LLMs on the UKET prediction task. The performance of zero-shot LLMs can be enhanced by integrating task-related information into few-shot examples. We hope that the CLC-UKET dataset, along with human annotations and empirical findings, can serve as a valuable benchmark for employment-related dispute resolution.

The CLC-UKET Dataset: Benchmarking Case Outcome Prediction for the UK Employment Tribunal

This study introduces a method for automating the consolidation process in a legal context, a time-consuming task traditionally performed by legal professionals. We present a genera- tive approach that processes legislative texts to automatically apply amendments. Our method employs light quantized generative model, fine- tuned with LoRA, to generate accurate and reli- able amended texts. To the authors knowledge, this is the first time generative models are used on legislative text consolidation. Our dataset is publicly available on HuggingFace1. Exper- imental results demonstrate a significant im- provement in efficiency, offering faster updates to legal documents. A full automated pipeline of legislative text consolidation can be done in a few hours, with a success rate of more than 63% on a difficult bill.

Algorithm for Automatic Legislative Text Consolidation

In this presentation, we outlined our approaches for the LegalLens 2024 shared-task. In the Legal Named Entity Recognition (L-NER) task, we combined a BERT-based language model with Conditional Random Fields, achieving first place. For the Legal Natural Language Inference (L-NLI) task, we employed data augmentation using GPT with novel prompting techniques to improve model performance, securing third place. In both tasks, We have evaluated various language models, including both general-purpose and legal domain-specific ones, in order to find the most effective approaches."

Enhancing Legal Violation Identification with LLMs and Deep Learning Techniques: Achievements in the LegalLens 2024 Competition

Despite the widespread availability of LLMs, there remains a substantial gap in their capabilities and availability across diverse languages. One approach to address these issues has been to take an existing pre-trained LLM and continue to train it on new languages. While prior works have experimented with language adaptation, many questions around best practices and methodology have not been covered. In this paper, we present a comprehensive investigation into the adaptation of LLMs to new languages. Our study covers the key components in this process, including vocabulary extension, direct preference optimization and the data scarcity problem for human alignment in low-resource languages. We scale these experiments across 9 languages and 2 parameter scales (7B and 70B). We compare our models against Llama 2, Aya-101, XGLM, BLOOM and existing language experts, outperforming all prior published baselines. Additionally, all evaluation code and checkpoints are made public to facilitate future research.

SambaLingo: Teaching Large Language Models New Languages

This paper investigates biases of Large Language Models (LLMs) through the lens of grammatical gender. Drawing inspiration from seminal works in psycholinguistics, particularly the study of gender's influence on language perception, we leverage multilingual LLMs to revisit and expand upon the foundational experiments of Boroditsky (2003). Employing LLMs as a novel method for examining psycholinguistic biases related to grammatical gender, we prompt a model to describe nouns with adjectives in various languages, focusing specifically on languages with grammatical gender. In particular, we look at adjective co-occurrences across gender and languages, and train a binary classifier to predict grammatical gender given adjectives an LLM uses to describe a noun. Surprisingly, we find that a simple classifier can not only predict noun gender above chance but also exhibit cross-language transferability. We show that while LLMs may describe words differently in different languages, they are biased similarly.

What an Elegant Bridge: Multilingual LLMs are Biased Similarly in Different Languages

Despite advancements in English-dominant generative large language models, further development is needed for low-resource languages to enhance global accessibility. The primary methods for representing these languages are monolingual and multilingual pretraining. Monolingual pretraining is expensive due to hardware requirements, and multilingual models often have uneven performance across languages. This study explores an alternative solution by adapting large language models, primarily trained on English, to low-resource languages. We assess various strategies, including continual training, instruction fine-tuning, task-specific fine-tuning, and vocabulary extension. The results show that continual training improves language comprehension, as reflected in perplexity scores, and task-specific tuning generally enhances performance of downstream tasks. However, extending the vocabulary shows no substantial benefits. Additionally, while larger models improve task performance with few-shot tuning, multilingual models perform worse than their monolingual counterparts when adapted.

Next from EMNLP 2024

Is artificial intelligence still intelligence? LLMs generalize to novel adjective-noun pairs, but don’t mimic the full human distribution

Similar lecture

A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models