United States

Detoxifying multilingual Large Language Models (LLMs) has become crucial due to their increasing global use. In this work, we explore zero-shot cross-lingual generalization of preference tuning in detoxifying LLMs. Unlike previous studies that show limited cross-lingual generalization for other safety tasks, we demonstrate that Direct Preference Optimization (DPO) training with only English data can significantly reduce toxicity in multilingual open-ended generations. For example, the probability of mGPT-1.3B generating toxic continuations drops from 46.8% to 3.9% across 17 different languages after training. Our results also extend to other multilingual LLMs, such as BLOOM, Llama3, and Aya-23. Using mechanistic interpretability tools like causal intervention and activation analysis, we identified the dual multilinguality property of MLP layers in LLMs, which explains the cross-lingual generalization of DPO. Finally, we show that bilingual sentence retrieval can predict the cross-lingual transferability of DPO preference tuning.

EMNLP 2024

Preference Tuning For Toxicity Mitigation Generalizes Across Languages

long-form generation

uncertainty

calibration

confidence estimation

large language models

evaluation

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

poster

## 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.

The goal of topic modeling is to find meaningful topics that capture the information present in a collection of documents. The main challenges of topic modeling are finding the optimal number of topics, labeling the topics, segmenting documents by topic, and evaluating topic model performance. Current neural approaches have tackled some of these problems but none have been able to solve all of them. We introduce a novel topic modeling approach, Contextual-Top2Vec, which uses document contextual token embeddings, it creates hierarchical topics, finds topic spans within documents and labels topics with phrases rather than just words. We propose the use of BERTScore to evaluate topic coherence and to evaluate how informative topics are of the underlying documents. Our model outperforms the current state-of-the-art models on a comprehensive set of topic model evaluation metrics.

Topic Modeling: Contextual Token Embeddings Are All You Need

Large Language Models (LLMs) internally store repositories of knowledge. However, their access to this repository is imprecise and they frequently hallucinate information that is not true or does not exist. A paradigm called Retrieval Augmented Generation (RAG) promises to fix these issues. Dense passage retrieval (DPR) is the first step in this paradigm. In this paper, we analyze the role of DPR fine-tuning and how it affects the model being trained. DPR fine-tunes pre-trained networks to enhance the alignment of the embeddings between queries and relevant textual data. We explore DPR-trained models mechanistically by using a combination of probing, layer activation analysis, and model editing. Our experiments show that DPR training \textbf{decentralizes} how knowledge is stored in the network, creating \textbf{multiple access pathways} to the same information. We also uncover a \textbf{limitation} in this training style: the \textbf{internal knowledge} of the pre-trained model \textbf{bounds} what the retrieval model can retrieve. These findings suggest a few possible directions for dense retrieval: (1) expose the DPR training process to more knowledge so more can be decentralized, (2) inject facts as decentralized representations, (3) model and incorporate knowledge uncertainty in the retrieval process, and (4) directly map internal model knowledge to a knowledge base.

Dense Passage Retrieval: Is it Retrieving?

Large Language Models (LLMs) have shown great potential in the biomedical domain with the advancement of retrieval-augmented generation (RAG). However, existing retrieval-augmented approaches face challenges in addressing diverse queries and documents, particularly for medical knowledge queries, resulting in sub-optimal performance. To address these limitations, we propose a novel plug-and-play LLM-based retrieval method called Self-Rewarding Tree Search (SeRTS) based on Monte Carlo Tree Search (MCTS) and a self-rewarding paradigm. By combining the reasoning capabilities of LLMs with the effectiveness of tree search, SeRTS boosts the zero-shot performance of retrieving high-quality and informative results for RAG. We further enhance retrieval performance by fine-tuning LLMs with Proximal Policy Optimization (PPO) objectives using the trajectories collected by SeRTS as feedback. Controlled experiments using the BioASQ-QA dataset with GPT-3.5-Turbo and LLama2-7b demonstrate that our method significantly improves the performance of the BM25 retriever and surpasses the strong baseline of self-reflection in both efficiency and scalability. Moreover, SeRTS generates higher-quality feedback for PPO training than self-reflection. Our proposed method effectively adapts LLMs to document retrieval tasks, enhancing their ability to retrieve highly relevant documents for RAG in the context of medical knowledge queries. This work presents a significant step forward in leveraging LLMs for accurate and comprehensive biomedical question answering.

Enhancing Biomedical Knowledge Retrieval-Augmented Generation with Self-Rewarding Tree Search and Proximal Policy Optimization

While current tasks of converting natural language to SQL (NL2SQL) using Foundation Models have shown impressive achievements, adapting these approaches for converting natural language to Graph Query Language (NL2GQL) encounters hurdles due to the distinct nature of GQL compared to SQL, alongside the diverse forms of GQL. Moving away from traditional rule-based and slot-filling methodologies, we introduce a novel approach, $R^3$-NL2GQL, integrating both small and large Foundation Models for ranking, rewriting, and refining tasks. This method leverages the interpretative strengths of smaller models for initial ranking and rewriting stages, while capitalizing on the superior generalization and query generation prowess of larger models for the final transformation of natural language queries into GQL formats. Addressing the scarcity of datasets in this emerging field, we have developed a bilingual dataset, sourced from graph database manuals and selected open-source Knowledge Graphs (KGs). Our evaluation of this methodology on this dataset demonstrates its promising efficacy and robustness.

R3-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL

Open-domain long-form text generation requires generating coherent, comprehensive responses that address complex queries with both breadth and depth. This task is challenging due to the need to accurately capture diverse facets of input queries. Existing iterative retrieval-augmented generation (RAG) approaches often struggle to delve deeply into each facet of complex queries and integrate knowledge from various sources effectively. This paper introduces ConTReGen, a novel framework that employs a context-driven, tree-structured retrieval approach to enhance the depth and relevance of retrieved content. ConTReGen integrates a hierarchical, top-down in-depth exploration of query facets with a systematic bottom-up synthesis, ensuring comprehensive coverage and coherent integration of multifaceted information. Extensive experiments on multiple datasets, including LFQA and ODSUM, alongside a newly introduced dataset, ODSUM-WikiHow, demonstrate that ConTReGen outperforms existing state-of-the-art RAG models.

ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation

Safety-aligned Large Language Models (LLMs) are still vulnerable to some manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. However, existing jailbreaking methods usually view a harmful prompt as a whole but they are not effective at reducing LLMs' attention on combinations of words with malice, which well-aligned LLMs can easily reject. This paper discovers that decomposing a malicious prompt into separated sub-prompts can effectively reduce LLMs' attention on harmful words by presenting them to LLMs in a fragmented form, thereby addressing these limitations and improving attack effectiveness. We introduce an automatic prompt Decomposition and Reconstruction framework for jailbreaking Attack (DrAttack). DrAttack consists of three key components: (a) 'Decomposition' of the original prompt into sub-prompts, (b) 'Reconstruction' of these sub-prompts implicitly by In-Context Learning with semantically similar but benign reassembling example, and (c) 'Synonym Search' of sub-prompts, aiming to find sub-prompts' synonyms that maintain the original intent while jailbreaking LLMs. An extensive empirical study across multiple open-source and closed-source LLMs demonstrates that, with fewer queries, DrAttack obtains a substantial gain of success rate on powerful LLMs over prior SOTA attackers. Notably, the success rate of 80% on GPT-4 surpassed previous art by 65%. Code and data are made publicly available at https://turningpoint-ai.github.io/DrAttack/.

DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLMs Jailbreakers

Large language models (LLMs) capable of casual conversation have recently become widely available. We hypothesize that users of conversational systems want a more personalized experience, and existing work shows that users are highly receptive to personalized questions (PQs). Question Generation tasks, however, focus on factual questions from textual excerpts. To create a PQ generator, we first identify over 400 real user interests by anonymously aggregating ~39K user models. We then populate prompt templates with these 400 interests and use an LLM to generate PQs customized to user interests. The result is PerQs, a novel corpus of ~19K question/answer pairs. We evaluate PerQs at scale in the unique context of the Alexa Prize. Our results show significant positive effects on perceived conversation quality. We then fine-tune, deploy, and evaluate PerQy, a neural model that generates PQs in real-time. When evaluated against several competitive LLM baselines, PerQy produced the most natural and engaging responses.

Active Listening: Personalized Question Generation in Open-Domain Social Conversation with User Model Based Prompting

Long-form question answering (LFQA) aims at generating in-depth answers to end-user questions, providing relevant information beyond the direct answer. However, existing retrievers are typically optimized towards information that directly targets the question, missing out on such contextual information. Furthermore, there is a lack of training data for relevant context. To this end, we propose and compare different weak supervision techniques to optimize retrieval for contextual information. Experiments demonstrate improvements on the end-to-end QA performance on ASQA, a dataset for long-form question answering. Importantly, as more contextual information is retrieved, we improve the relevant page recall for LFQA by 14.7% and the groundedness of generated long-form answers by 12.5%. Finally, we show that long-form answers often anticipate likely follow-up questions, via experiments on a conversational QA dataset.

Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision

Despite their remarkable capabilities, Large Language Models (LLMs) are found to be surprisingly sensitive to minor variations in prompts, often generating significantly divergent outputs in response to minor variations in the prompts, such as spelling errors, alteration of wording or the prompt template. However, while assessing the quality of an LLM, the focus often tends to be solely on its performance on downstream tasks, while very little to no attention is paid to prompt sensitivity. To fill this gap, we propose POSIX – a novel PrOmpt Sensitivity IndeX as a reliable measure of prompt sensitivity, thereby offering a more comprehensive evaluation of LLM performance. The key idea behind POSIX is to capture the relative change in loglikelihood of a given response upon replacing the corresponding prompt with a different intent-preserving prompt. We provide thorough empirical evidence demonstrating the efficacy of POSIX in capturing prompt sensitivity and subsequently use it to measure and thereby compare prompt sensitivity of various open source LLMs. We find that merely increasing the parameter count or instruction tuning does not necessarily reduce prompt sensitivity whereas adding some few-shot exemplars, even just one, almost always leads to significant decrease in prompt sensitivity. We also find that alterations to prompt template lead to the highest sensitivity in the case of MCQ type tasks, whereas paraphrasing results in the highest sensitivity in open-ended generation tasks. The code for reproducing our results is open-sourced at https://github.com/kowndinya-renduchintala/POSIX.

POSIX: A Prompt Sensitivity Index For Large Language Models

Large language models (LLMs) equipped with chain-of-thoughts (CoT) prompting have shown significant multi-step reasoning capabilities in factual content like mathematics, commonsense, and logic. However, their performance in narrative reasoning, which demands greater abstraction capabilities, remains unexplored. This study utilizes tropes in movie synopses to assess the abstract reasoning abilities of state-of-the-art LLMs and uncovers their low performance. We introduce a trope-wise querying approach to address these challenges and boost the F1 score by 11.8 points. Moreover, while prior studies suggest that CoT enhances multi-step reasoning, this study shows CoT can cause hallucinations in narrative content, reducing GPT-4's performance. We also introduce an Adversarial Injection method to embed trope-related text tokens into movie synopses without explicit tropes, revealing CoT's heightened sensitivity to such injections. Our comprehensive analysis provides insights for future research directions.

Downloads

Next from EMNLP 2024

Topic Modeling: Contextual Token Embeddings Are All You Need

Similar lecture

How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis