EMNLP 2024 Papers

Large language models (LLMs) sometimes demonstrate poor performance on knowledge-intensive tasks, commonsense reasoning is one of them. Researchers typically address these issues by retrieving related knowledge from knowledge graphs or employing self-enhancement methods to elicit knowledge in LLMs. However, noisy knowledge and invalid reasoning issues hamper their ability to answer questions accurately. To this end, we propose a novel method named eliciting, filtering and integrating knowledge in large language model (LINKED). In it, we design a reward model to filter out the noisy knowledge and take the marginal consistent reasoning module to reduce invalid reasoning. With our comprehensive experiments on two complex commonsense reasoning benchmarks, our method outperforms SOTA baselines (up to 9.0% improvement of accuracy). Besides, to measure the positive and negative impact of the injected knowledge, we propose a new metric called effectiveness-preservation score for the knowledge enhancement works. Finally, through extensive experiments, we conduct an in-depth analysis and find many meaningful conclusions about LLMs in commonsense reasoning tasks.

Non-Factoid (NF) Question Answering (QA) is challenging to evaluate due to diverse potential answers and no objective criterion. The commonly used automatic evaluation metrics like ROUGE or BERTScore cannot accurately measure semantic similarities or answers from different perspectives. Recently, Large Language Models (LLMs) have been resorted to for NFQA evaluation due to their compelling performance on various NLP tasks. Common approaches include pointwise scoring of each candidate answer and pairwise comparisons between answers. Inspired by the evolution from pointwise to pairwise to listwise in learning-to-rank methods, we propose a novel listwise NFQA evaluation approach, that utilizes LLMs to rank candidate answers in a list of reference answers sorted by descending quality. Moreover, for NF questions that do not have multi-grade or any golden answers, we leverage LLMs to generate the reference answer list of various quality to facilitate the listwise evaluation. Extensive experimental results on three NFQA datasets, i.e., ANTIQUE, the TREC-DL-NF, and WebGLM show that our method has significantly higher correlations with human annotations compared to automatic scores and common pointwise and pairwise approaches.

Large language models (LLMs) require continual knowledge updates to stay abreast of the ever-changing world facts, prompting the formulation of lifelong model editing task. While recent years have witnessed the development of various techniques for single and batch editing, these methods either fail to apply or perform sub-optimally when faced with lifelong editing. In this paper, we introduce LEMoE, an advanced Mixture of Experts (MoE) adaptor for lifelong model editing. We first analyze the factors influencing the effectiveness of conventional MoE adaptor in lifelong editing, including catastrophic forgetting, inconsistent routing and order sensitivity. Based on these insights, we propose a tailored module insertion method to achieve lifelong editing, incorporating a novel KV anchor routing to enhance routing consistency between training and inference stage, along with a concise yet effective clustering-based editing order planning. Experimental results demonstrate the effectiveness of our method in lifelong editing, surpassing previous model editing techniques while maintaining outstanding performance in batch editing task. Our code will be available.

The ever-increasing volume of paper submissions makes it difficult to stay informed about the latest state-of-the-art research. To address this challenge, we introduce LEGOBench, a benchmark for evaluating systems that generate scientific leaderboards. LEGOBench is curated from 22 years of preprint submission data on arXiv and more than 11k machine learning leaderboards on the PapersWithCode portal. We present a language model-based and four graph-based leaderboard generation task configuration. We evaluate popular encoder-only scientific language models as well as decoder-only large language models across these task configurations. State-of-the-art models showcase significant performance gaps in automatic leaderboard generation on LEGOBench. The code is available on GitHub and the dataset is hosted on OSF.

Multi-turn intent classification is notably challenging due to the complexity and evolving nature of conversational contexts. This paper introduces LARA, a Linguistic-Adaptive Retrieval-Augmentation framework to enhance accuracy in multi-turn classification tasks across six languages, accommodating numerous intents in chatbot interactions. LARA combines a fine-tuned smaller model with a retrieval-augmented mechanism, integrated within the architecture of LLMs. The integration allows LARA to dynamically utilize past dialogues and relevant intents, thereby improving the understanding of the context. Furthermore, our adaptive retrieval techniques bolster the cross-lingual capabilities of LLMs without extensive retraining and fine-tuning. Comprehensive experiments demonstrate that LARA achieves state-of-the-art performance on multi-turn intent classification tasks, enhancing the average accuracy by 3.67% from state-of-the-art single-turn intent classifiers.

Multi-modal machine translation (MMT) can reduce ambiguity and semantic distortion compared with traditional machine translation (MT) by utilizing auxiliary information such as images. However, current MMT methods face two primary challenges. The first is their underperformance compared to MT methods based on pre-trained models. The second is the inadequate exploitation and integration of the image modality within the model, primarily due to a lack of triplet training data. A mainstream approach is to introduce large amounts of parallel and monolingual data to train the text model and the visual model separately. However, incorporating extensive external data can result in data imbalance, which may introduce biases during training. Additionally, the collection and cleaning of such large datasets is labor-intensive. To overcome these challenges, we introduce a novel, low-cost, large language model-based data augmentation method called LAMBDA, which can enrich the original samples and expand the dataset without requiring external images and text. We propose a fine-grained image captioning module with a noise filter to hierarchically and accurately extract unexploited information from images. Additionally, we design two specific prompts to guide the GPT-3.5 model in generating enriched texts and the corresponding translations. The enriched samples contain diverse text and strong connections between text and images, leading to significant improvements for MMT baselines, with the highest being an increase of up to 3.83 BLEU score and 3.61 METEOR score.

To mitigate the annual financial losses caused by SMS phishing (smishing) in South Korea, we propose an explainable smishing detection framework that adapts to a Korean-centric large language model (LLM). Our framework not only classifies smishing attempts but also provides clear explanations, enabling users to identify and understand these threats. This end-to-end solution encompasses data collection, pseudo-label generation, and parameter-efficient task adaptation for models with fewer than five billion parameters. Our approach achieves a 15% improvement in accuracy over GPT-4 and generates high-quality explanatory text, as validated by seven automatic metrics and qualitative evaluation, including human assessments.

The success of large language models (LLMs) facilitate many parties to fine-tune LLMs on their own private data. However, this practice raises privacy concerns due to the memorization of LLMs. Existing solutions, such as utilizing synthetic data for substitution, struggle to simultaneously improve performance and preserve privacy.They either rely on a local model for generation, resulting in a performance decline, or take advantage of APIs, directly exposing the data to API servers. To address this issue, we propose KnowledgeSG, a novel client-server framework which enhances synthetic data quality and improves model performance while ensuring privacy. We achieve this by learning local knowledge from the private data with differential privacy (DP) and distilling professional knowledge from the server. Additionally, inspired by federated learning, we transmit models rather than data between the client and server to prevent privacy leakage.Extensive experiments in medical and financial domains demonstrate the effectiveness of *KnowledgeSG*. Our code is now publicly available at https://github.com/wwh0411/KnowledgeSG.

In this work, we systematically expose and measure the inconsistency and knowledge gaps of Large Language Models (LLMs). Specifically, we propose an automated testing framework (called KONTEST) which leverages a knowledge graph to construct test cases. KONTEST probes and measures the inconsistencies in the LLM’s knowledge of the world via a combination of semantically-equivalent queries and test oracles (metamorphic or ontological oracle). KONTEST further mitigates knowledge gaps via a weighted LLM model ensemble. Using four state-of-the-art LLMs (Falcon, Gemini, GPT3.5, and Llama2), we show that KONTEST generates 19.2% error inducing inputs (1917 errors from 9979 test inputs). It also reveals a 16.5% knowledge gap across all tested LLMs. A mitigation method informed by KONTEST’s test suite reduces LLM knowledge gap by 32.48%. Our ablation study further shows that GPT3.5 is not suitable for knowledge-based consistency testing because it is only 60%-68% effective in knowledge construction.

Crafting a convincing financial market analysis report necessitates a wealth of market information and the expertise of financial analysts, posing a highly challenging task. While large language models (LLMs) have enabled the automated generation of financial market analysis text, they still face issues such as hallucinations, errors in financial knowledge, and insufficient capability to reason about complex financial problems, which limits the quality of the generation. To tackle these shortcomings, we propose a novel task and a retrieval-augmented framework grounded in a financial knowledge graph (FKG). The proposed framework is compatible with commonly used instruction-tuning methods. Experiments demonstrate that our framework, coupled with a small-scale language model fine-tuned with instructions, can significantly enhance the logical consistency and quality of the generated analysis texts, outperforming both large-scale language models and other retrieval-augmented baselines.

Multimodal Sentiment Analysis (MSA) utilizes multimodal data to infer the users’ sentiment. Previous methods focus on equally treating the contribution of each modality or statically using text as the dominant modality to conduct interaction, which neglects the situation where each modality may become dominant. In this paper, we propose a Knowledge-Guided Dynamic Modality Attention Fusion Framework (KuDA) for multimodal sentiment analysis. KuDA uses sentiment knowledge to guide the model dynamically selecting the dominant modality and adjusting the contributions of each modality. In addition, with the obtained multimodal representation, the model can further highlight the contribution of dominant modality through the correlation evaluation loss. Extensive experiments on four MSA benchmark datasets indicate that KuDA achieves state-of-the-art performance and is able to adapt to different scenarios of dominant modality.

Authors seeking to communicate with broader audiences often share their ideas in various document formats, such as slide decks, newsletters, reports, and posters. Prior work on document generation has generally tackled the creation of each separate format to be a different task, leading to fragmented learning processes, redundancy in models and methods, and disjointed evaluation. We consider each of these documents as templatic views of the same underlying knowledge/content, and we aim to unify the generation and evaluation of these templatic views. We begin by showing that current LLMs are capable of generating various document formats with little to no supervision. Further, a simple augmentation involving a structured intermediate representation can improve performance, especially for smaller models. We then introduce a novel unified evaluation framework that can be adapted to measuring the quality of document generators for heterogeneous downstream applications. This evaluation is adaptable to a range of user defined criteria and application scenarios, obviating the need for task specific evaluation metrics. Finally, we conduct a human evaluation, which shows that people prefer 82% of the documents generated with our method, while correlating more highly with our unified evaluation framework than prior metrics in the literature.

Large Language Models (LLMs) have shown impressive capabilities but also a concerning tendency to hallucinate. This paper presents RefChecker, a framework that introduces claim-triplets to represent claims in LLM responses, aiming to detect fine-grained hallucinations. In RefChecker, an extractor generates claim-triplets from a response, which are then evaluated by a checker against a reference. We delineate three task settings: Zero, Noisy and Accurate Context, to reflect various real-world use cases. We curated a benchmark spanning various NLP tasks and annotated 11k claim-triplets from 2.1k responses by seven LLMs. RefChecker supports both proprietary and open-source models as the extractor and checker. Experiments demonstrate that claim-triplets enable superior hallucination detection, compared to other granularities such as response, sentence and sub-sentence level claims. RefChecker outperforms prior methods by 18.2 to 27.2 points on our benchmark and the checking results of RefChecker are strongly aligned with human judgments.

Existing datasets for tabular question answering typically focus exclusively on text within cells. However, real-world data is inherently multimodal, often blending images such as symbols, faces, icons, patterns, and charts with textual content in tables. With the evolution of AI models capable of multimodal reasoning, it is pertinent to assess their efficacy in handling such structured data. This study investigates whether current AI models can perform knowledge-aware reasoning on multimodal structured data. We explore their ability to reason on tables that integrate both images and text, introducing MMTabQA, a new dataset designed for this purpose. Our experiments highlight substantial challenges for current AI models in effectively integrating and interpreting multiple text and image inputs, understanding visual context, and comparing visual content across images. These findings establish our dataset as a robust benchmark for advancing AI’s comprehension and capabilities in analyzing multimodal structured data.

While large language models (LLMs) have demonstrated exceptional performance across various tasks following human alignment, they may still generate responses that sound plausible but contradict factual knowledge, a phenomenon known as hallucination. In this paper, we demonstrate the feasibility of mitigating hallucinations by verifying and minimizing the inconsistency between external knowledge present in the alignment data and the intrinsic knowledge embedded within foundation LLMs. Specifically, we propose a novel approach called Knowledge Consistent Alignment (KCA), which employs a well-aligned LLM to automatically formulate assessments based on external knowledge to evaluate the knowledge boundaries of foundation LLMs. To address knowledge inconsistencies in the alignment data, KCA implements several specific strategies to deal with these data instances. We demonstrate the superior efficacy of KCA in reducing hallucinations across six benchmarks, utilizing foundation LLMs of varying backbones and scales. This confirms the effectiveness of mitigating hallucinations by reducing knowledge inconsistency. Our code, model weights, and data are openly accessible at https://github.com/fanqiwan/KCA.

In mental health counseling, condensing dialogues into concise and relevant summaries (aka counseling notes) holds pivotal significance. Large Language Models (LLMs) exhibit remarkable capabilities in various generative tasks; however, their adaptation to domain-specific intricacies remains challenging, especially within mental health contexts. Unlike standard LLMs, mental health experts first plan to apply domain knowledge in writing summaries. Our work enhances LLMs’ ability by introducing a novel planning engine to orchestrate structuring knowledge alignment. To achieve high-order planning, we divide knowledge encapsulation into two major phases: (i) holding dialogue structure and (ii) incorporating domain-specific knowledge. We employ a planning engine on Llama-2, resulting in a novel framework, PIECE. Our proposed system employs knowledge filtering-cum-scaffolding to encapsulate domain knowledge. Additionally, PIECE leverages sheaf convolution learning to enhance its understanding of the dialogue’s structural nuances. We compare PIECE with 14 baseline methods and observe a significant improvement across ROUGE and Bleurt scores. Further, expert evaluation and analyses validate the generation quality to be effective, sometimes even surpassing the gold standard. We further benchmark PIECE with other LLMs and report improvement, including Llama-2 (+2.72%), Mistral (+2.04%), and Zephyr (+1.59%), to justify the generalizability of the planning engine.

The exponential growth of scientific literature necessitates advanced tools for effective knowledge exploration. We present Knowledge Navigator, a system designed to enhance exploratory search abilities by organizing and structuring the retrieved documents from broad topical queries into a navigable, two-level hierarchy of named and descriptive scientific topics and subtopics. This structured organization provides an overall view of the research themes in a domain, while also enabling iterative search and deeper knowledge discovery within specific subtopics by allowing users to refine their focus and retrieve additional relevant documents. Knowledge Navigator combines LLM capabilities with cluster-based methods to enable an effective browsing method. We demonstrate our approach’s effectiveness through automatic and manual evaluations on two novel benchmarks, CLUSTREC-COVID and SCITOC Our code, prompts, and benchmarks are made publicly available.

Understanding knowledge mechanisms in Large Language Models (LLMs) is crucial for advancing towards trustworthy AGI. This paper reviews knowledge mechanism analysis from a novel taxonomy including knowledge utilization and evolution. Knowledge utilization delves into the mechanism of memorization, comprehension and application, and creation. Knowledge evolution focuses on the dynamic progression of knowledge within individual and group LLMs. Moreover, we discuss what knowledge LLMs have learned, the reasons for the fragility of parametric knowledge, and the potential dark knowledge (hypothesis) that will be challenging to address. We hope this work can help understand knowledge in LLMs and provide insights for future research.

Large language models (LLMs) are pivotal in advancing natural language processing (NLP) tasks, yet their efficacy is hampered by inaccuracies and outdated knowledge. Model editing emerges as a promising solution to address these challenges. However, existing editing methods struggle to track and incorporate changes in knowledge associated with edits, which limits the generalization ability of post-edit LLMs in processing edited knowledge. To tackle these problems, we propose a novel model editing method that leverages knowledge graphs for enhancing LLM editing, namely GLAME. Specifically, we first utilize a knowledge graph augmentation module to uncover associated knowledge that has changed due to editing, obtaining its internal representations within LLMs. This approach allows knowledge alterations within LLMs to be reflected through an external graph structure. Subsequently, we design a graph-based knowledge edit module to integrate structured knowledge into the model editing. This ensures that the updated parameters reflect not only the modifications of the edited knowledge but also the changes in other associated knowledge resulting from the editing process. Comprehensive experiments conducted on GPT-J and GPT-2 XL demonstrate that GLAME significantly improves the generalization capabilities of post-edit LLMs in employing edited knowledge.