United States

Information-Seeking Dialogue (ISD) agents aim to provide accurate responses to user queries. While proficient in directly addressing user queries, these agents, as well as LLMs in general, predominantly exhibit reactive behavior, lacking the ability to generate proactive responses that actively engage users in sustained conversations. However, existing definitions of proactive dialogue in this context do not focus on how each response actively engages the user and sustains the conversation. Hence, we present a new definition of proactivity that focuses on enhancing the `proactiveness&#39; of each generated response via the introduction of new information related to the initial query. To this end, we construct a proactive dialogue dataset comprising 2,000 single-turn conversations, and introduce several automatic metrics to evaluate response &#39;proactiveness&#39; which achieved high correlation with human annotation. Additionally, we introduce two innovative Chain-of-Thought (CoT) prompts, the 3-step CoT and the 3-in-1 CoT prompts, which consistently outperform standard prompts by up to 90% in the zero-shot setting.

EMNLP 2024

Redefining Proactivity for Information Seeking Dialogue

information seeking dialogue

llms

Information-Seeking Dialogue (ISD) agents aim to provide accurate responses to user queries. While proficient in directly addressing user queries, these agents, as well as LLMs in general, predominantly exhibit reactive behavior, lacking the ability to generate proactive responses that actively engage users in sustained conversations. However, existing definitions of proactive dialogue in this context do not focus on how each response actively engages the user and sustains the conversation. Hence, we present a new definition of proactivity that focuses on enhancing the `proactiveness' of each generated response via the introduction of new information related to the initial query. To this end, we construct a proactive dialogue dataset comprising 2,000 single-turn conversations, and introduce several automatic metrics to evaluate response 'proactiveness' which achieved high correlation with human annotation. Additionally, we introduce two innovative Chain-of-Thought (CoT) prompts, the 3-step CoT and the 3-in-1 CoT prompts, which consistently outperform standard prompts by up to 90% in the zero-shot setting.

## 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.

Code-mixing (CM), where speakers blend languages within a single expression, is prevalent in multilingual societies but poses challenges for natural language processing due to its complexity and limited data. We propose using a large language model to generate synthetic CM data, which is then used to enhance the performance of task-specific models for CM sentiment analysis. Our results show that in Spanglish, synthetic data improved the F1 score by 9.32\%, outperforming previous augmentation techniques. However, in Malayalam-English, synthetic data only helped when the baseline was low; with strong natural data, additional synthetic data offered little benefit. Human evaluation confirmed that this approach is a simple, cost-effective way to generate natural-sounding CM sentences, particularly beneficial for low baselines. Our findings suggest that few-shot prompting of large language models is a promising method for CM data augmentation and has significant impact on improving sentiment analysis, an important element in the development of social influence systems.

Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis

The unchecked spread of digital information, combined with increasing political polariza- tion and the tendency of individuals to iso- late themselves from opposing political view- points, has driven researchers to develop sys- tems for automatically detecting political bias in media. This trend has been further fueled by discussions on social media. We explore methods for categorizing bias in US news arti- cles, comparing rule-based and deep learning approaches. The study highlights the sensi- tivity of modern self-learning systems to un- constrained data ingestion, while reconsider- ing the strengths of traditional rule-based sys- tems. Applying both models to left-leaning (CNN) and right-leaning (FOX) news articles, we assess their effectiveness on data beyond the original training and test sets. This analy- sis highlights each model’s accuracy, offers a framework for exploring deep-learning explain- ability, and sheds light on political bias in US news media. We contrast the opaque architec- ture of a deep learning model with the trans- parency of a linguistically informed rule-based model, showing that the rule-based model per- forms consistently across different data condi- tions and offers greater transparency, whereas the deep learning model is dependent on the training set and struggles with unseen data.

Balancing Transparency and Accuracy: A Comparative Analysis of Rule-Based and Deep Learning Models in Political Bias Classification

AI chatbots are increasingly designed to exhibit human-like traits such as empathy. However, how users perceive the empathy of these chatbots, and how this affects users' feelings about the conversation with them, has not been thoroughly examined. This study examines how the identity and perceived empathy of a chatbot affect human perceptions of the overall conversation quality. We analyzed 154 conversations from two datasets and found that, although GPT-based chatbots were rated significantly higher in overall conversational quality, they were perceived by users as having lower empathy compared to their human counterparts. Ratings of empathy from GPT-4o annotation align with human assessments, demonstrating a consistent perception of lower empathy in chatbots. However, off-the-shelf empathy models trained human-human conversations found no differences in perceived empathy in language between chatbots and humans. Our research emphasizes the importance of perceived empathy in influencing overall conversation quality. Managing perceived empathy in human-AI interactions is complex; creating chatbots that are perceived as high-conversational quality involves more than simply using empathetic language.

The Illusion of Empathy: How AI Chatbots Shape Conversation Perception

Large Language Models (LLMs) excel at a range of tasks but often struggle with issues like hallucination and inadequate empathy support. To address hallucinations, we ground our dialogues in medical knowledge sourced from external repositories such as Disease Ontology and DrugBank. To improve empathy support, we develop the Empathetic Healthcare Dialogues dataset, which utilizes multiple dialogue strategies in each response. This dataset is then used to fine-tune an LLM, and we introduce a lightweight, adaptable method called Strategy Combination Guidance to enhance the emotional support capabilities of the fine-tuned model, named EHDChat. Our evaluations show that EHDChat significantly outperforms existing models in providing emotional support and medical accuracy, demonstrating the effectiveness of our approach in enhancing empathetic and informed AI interactions in healthcare.

EHDChat: A Knowledge-Grounded, Empathy-Enhanced Language Model for Healthcare Interactions

Aspect Sentiment Triplet Extraction (ASTE) is a challenging task in sentiment analysis, aiming to provide fine-grained insights into human sentiments. However, existing benchmarks are limited to two domains and do not evaluate model performance on unseen domains, raising concerns about the generalization of proposed methods. Furthermore, it remains unclear if large language models (LLMs) can effectively handle complex sentiment tasks like ASTE. In this work, we address the issue of generalization in ASTE from both a benchmarking and modeling perspective. We introduce a domain-expanded benchmark by annotating samples from diverse domains, enabling evaluation of models in both in-domain and out-of-domain settings. Additionally, we propose CASE, a simple and effective decoding strategy that enhances trustworthiness and performance of LLMs in ASTE. Through comprehensive experiments involving multiple tasks, settings, and models, we demonstrate that CASE can serve as a general decoding strategy for complex sentiment tasks. By expanding the scope of evaluation and providing a more reliable decoding strategy, we aim to inspire the research community to reevaluate the generalizability of benchmarks and models for ASTE. Our code, data, and models are available at https://github.com/DAMO-NLP-SG/domain-expanded-aste.

Domain-Expanded ASTE: Rethinking Generalization in Aspect Sentiment Triplet Extraction

East Asian idioms are a type of figurative language, each condensing its rich cultural background into a few characters. Translating such idioms is challenging for human translators, who often resort to choosing a context-aware translation from an existing list of candidates. However, compiling a dictionary of translations demands much time and creativity even for expert translators. To alleviate such burden, we evaluate if GPT-4 can help generate high-quality translations. Based on automatic evaluations of faithfulness and creativity, we first identify Pareto-optimal prompting strategies that can outperform translation engines from Google and DeepL. Then, at a low cost, our context-aware translations can achieve far more and higher-quality translations per idiom than the human baseline. We open-source all code and data to facilitate further research.

Creative and Context-Aware Translation of East Asian Idioms with GPT-4

In this paper, we discuss multilingual vocabulary for neural machine translation models. Multilingual vocabularies should generate highly accurate machine translations regardless of the languages, and have preferences so that tokenized strings contain rare out-of-vocabulary (OOV) tokens and token sequences are short. In this paper, we discuss the characteristics of various multilingual vocabularies via tokenization and translation experiments. We also present our recommended vocabulary and tokenizer.

An Empirical Study of Multilingual Vocabulary for Neural Machine Translation Models

Many low-resource languages, such as Prakrit, present significant linguistic complexities and have limited modern-day resources. These languages often have multiple derivatives; for example, Prakrit, a language in use by masses around 2500 years ago for 500 years, includes Pali, Gandhari, and Tibetan, which encompass a vast body of Buddhist literature, as well as Ardhamagadhi, rich in Jain literature. Despite these challenges, these languages are invaluable for their historical, religious, and cultural insights needed by non-language experts and others.

To explore and understand the deep knowledge within these ancient texts for non-language experts, we propose a novel approach: translating multiple dialects of the parent language into a contemporary language and then enabling them to interact with the system in their native language, including English, Hindi, French and German, through a question-and-answer interface built on Large Language Models. We demonstrate the effectiveness of this novel AI-Tutor system by focusing on Ardhamagadhi and Pali.

AI-Tutor: Interactive Learning of Ancient Knowledge from Low-Resource Languages

Large language models excel at creative generation but continue to struggle with the issues of hallucination and bias. While retrievalaugmented generation (RAG) provides a framework for grounding LLMs’ responses in accurate and up-to-date information, it still raises the question of bias: which sources should be selected for inclusion in the context? And how should their importance be weighted? In this paper, we study the challenge of cross-lingual RAG and present a dataset to investigate the robustness of existing systems at answering queries about geopolitical disputes, which exist at the intersection of linguistic, cultural, and political boundaries. Our dataset is sourced from Wikipedia pages containing information relevant to the given queries and we investigate the impact of including additional context, as well as the composition of this context in terms of language and source, on an LLM’s response. Our results show that existing RAG systems continue to be challenged by crosslingual use cases and suffer from a lack of consistency when they are provided with competing information in multiple languages. We present case studies to illustrate these issues and outline steps for future research to address these challenges. We make our dataset and code publicly available.

BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval Augmented Generation

Taxonomies of scientific research seek to describe complex domains of activity that are overlapping and dynamic. We address this challenge by combining knowledge curated by the Wikipedia community with the input of subject-matter experts to identify, define, and validate a system of 1,110 granular fields of study for use in multi-label classification of scientific publications. The result is capable of categorizing research across subfields of artificial intelligence, computer security, semiconductors, genetics, virology, immunology, neuroscience, biotechnology, and bioinformatics. We then develop and evaluate a solution for zero-shot classification of publications in terms of these fields.

Premium content

Redefining Proactivity for Information Seeking Dialogue

Downloads

Next from EMNLP 2024

Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES