United States

Jailbreak attacks enable malicious queries to evade detection by LLMs. Existing attacks focus on meticulously constructing prompts to disguise harmful intentions. However, the incorporation of sophisticated disguising prompts may incur the challenge of &quot;intention shift&quot;. Intention shift occurs when the additional semantics within the prompt distract the LLMs, causing the responses to deviate significantly from the original harmful intentions. In this paper, we propose a novel component, &quot;bait&quot;, to alleviate the effects of intention shift. Bait comprises an initial response to the harmful query, prompting LLMs to rectify or supplement the knowledge within the bait. By furnishing rich semantics relevant to the query, the bait helps LLMs focus on the original intention. To conceal the harmful content within the bait, we further propose a novel attack paradigm, BaitAttack. BaitAttack adaptively generates necessary components to persuade targeted LLMs that they are engaging with a legitimate inquiry in a safe context. Our proposal is evaluated on a popular dataset, demonstrating state-of-the-art attack performance and an exceptional capability for mitigating intention shift. The implementation of BaitAttack is accessible at: https://anonymous.4open.science/r/BaitAttack-D1F5.

EMNLP 2024

BaitAttack: Alleviating Intention Shift in Jailbreak Attacks via Adaptive Bait Crafting

robotics and beyond

multimodality and language grounding to vision

and fairness

resources and evaluation

ethics

bias

Jailbreak attacks enable malicious queries to evade detection by LLMs. Existing attacks focus on meticulously constructing prompts to disguise harmful intentions. However, the incorporation of sophisticated disguising prompts may incur the challenge of "intention shift". Intention shift occurs when the additional semantics within the prompt distract the LLMs, causing the responses to deviate significantly from the original harmful intentions. In this paper, we propose a novel component, "bait", to alleviate the effects of intention shift. Bait comprises an initial response to the harmful query, prompting LLMs to rectify or supplement the knowledge within the bait. By furnishing rich semantics relevant to the query, the bait helps LLMs focus on the original intention. To conceal the harmful content within the bait, we further propose a novel attack paradigm, BaitAttack. BaitAttack adaptively generates necessary components to persuade targeted LLMs that they are engaging with a legitimate inquiry in a safe context. Our proposal is evaluated on a popular dataset, demonstrating state-of-the-art attack performance and an exceptional capability for mitigating intention shift. The implementation of BaitAttack is accessible at: https://anonymous.4open.science/r/BaitAttack-D1F5.

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.

Mixture-of-Experts (MoE) has gained increasing popularity as a promising framework for scaling up large language models (LLMs). However, training MoE from scratch in a large-scale setting still suffers from data-hungry and instability problems. Motivated by this limit, we investigate building MoE models from existing dense large language models. Specifically, based on the well-known LLaMA-2 7B model, we obtain an MoE model by: (1) Expert Construction, which partitions the parameters of original Feed-Forward Networks (FFNs) into multiple experts; (2) Continual pre-training, which further trains the transformed MoE model and additional gate networks. In this paper, we comprehensively explore different methods for expert construction and various data sampling strategies for continual pre-training. After these stages, our LLaMA-MoE models could maintain language abilities and route the input tokens to specific experts with part of the parameters activated. Empirically, by training 200B tokens, LLaMA-MoE-3.5B models significantly outperform dense models that contain similar activation parameters.

LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-Training

In the rapidly evolving domain of Natural Language Generation (NLG) evaluation, introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e.g., coherence, creativity, and context relevance. This paper aims to provide a thorough overview of leveraging LLMs for NLG evaluation, a burgeoning area that lacks a systematic analysis. We propose a coherent taxonomy for organizing existing LLM-based evaluation metrics, offering a structured framework to understand and compare these methods. Our detailed exploration includes critically assessing various LLM-based methodologies, as well as comparing their strengths and limitations in evaluating NLG outputs. By discussing unresolved challenges, including bias, robustness, domain-specificity, and unified evaluation, this paper seeks to offer insights to researchers and advocate for fairer and more advanced NLG evaluation techniques.

Leveraging Large Language Models for NLG Evaluation: Advances and Challenges

Recently, LLMs have significantly improved code generation, making it increasingly accessible to users. As a result, LLM-powered code generation applications have sprung up, vastly boosting user productivity. This paper mainly explores how to improve the efficiency and experience of users in formatting the document. Specifically, we propose an automatic document formatting method, Text-to-Format, which is driven by various prompting strategies. Text-to-Format takes the user's formatting instructions and then generates code that can be run in Microsoft Word to format the content in a document. Further, to evaluate automatic document formatting approaches and advance the document formatting task, we built an evaluation specification including a high-quality dataset DocFormEval data, a code runtime environment, and evaluation metrics. Extensive experimental results on data reveal that the prompting strategy's effect positively correlates with how much knowledge it introduces related to document formatting task. We believe the constructed DocFormEval data and the exploration about Text-to-Format can help developers build more intelligent tools for automatic document formatting, especially in offline scenarios, where the data privacy is the top priority.

Free your mouse! Command Large Language Models to Generate Code to Format Word Documents

The interest in linear complexity models for large language models is on the rise, although their scaling capacity remains uncertain. In this study, we present the scaling laws for linear complexity language models to establish a foundation for their scalability. Specifically, we examine the scaling behaviors of three efficient linear architectures. These include TNL, a linear attention model with data-independent decay; HGRN2, a linear RNN with data-dependent decay; and cosFormer2, a linear attention model without decay. We also include LLaMA as a baseline architecture for comparison with softmax attention. These models were trained with six variants, ranging from 70M to 7B parameters on a 300B-token corpus, and evaluated with a total of 1,376 intermediate checkpoints on various downstream tasks. These tasks include validation loss, commonsense reasoning, and information retrieval and generation. The study reveals that existing linear complexity language models exhibit similar scaling capabilities as conventional transformer-based models while also demonstrating superior linguistic proficiency and knowledge retention.

Scaling Laws for Linear Complexity Language Models

With the rise of globalisation, code-switching (CSW) has become a ubiquitous part of multilingual conversation, posing new challenges for natural language processing (NLP), especially in Grammatical Error Correction (GEC). This work explores the complexities of applying GEC systems to CSW texts. Our objectives include evaluating the performance of state-of-the-art GEC systems on an authentic CSW dataset from English as a Second Language (ESL) learners, exploring synthetic data generation as a solution to data scarcity, and developing a model capable of correcting grammatical errors in monolingual and CSW texts. We generated synthetic CSW GEC data, resulting in one of the first substantial datasets for this task, and showed that a model trained on this data is capable of significant improvements over existing systems. This work targets ESL learners, aiming to provide educational technologies that aid in the development of their English grammatical correctness without constraining their natural multilingualism.

LLM-based Code-Switched Text Generation for Grammatical Error Correction

Recent breakthroughs in preference alignment have significantly improved Large Language Models' ability to generate texts that align with human preferences and values. However, current alignment metrics typically emphasize the post-hoc overall improvement, while overlooking a critical aspect: $\textit{regression}$, which refers to the backsliding on previously correctly-handled data after updates. This potential pitfall may arise from excessive fine-tuning on already well-aligned data, which subsequently leads to over-alignment and degeneration. To address this challenge, we propose $\textit{FlipGuard}$, a constrained optimization approach to detect and mitigate update regression with focal attention. Specifically, FlipGuard identifies performance degradation using a customized reward characterization and strategically enforces a constraint to encourage conditional congruence with the pre-aligned model during training. Comprehensive experiments demonstrate that FlipGuard effectively alleviates update regression while demonstrating excellent overall performance, with the added benefit of knowledge preservation while aligning preferences.

FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization

Aligning large language models (LLMs) with human expectations requires high-quality instructional dialogues, which can be achieved by raising diverse, in-depth, and insightful instructions that deepen interactions. Existing methods target instructions from real instruction dialogues as a learning goal and fine-tune a user simulator for posing instructions. However, the user simulator struggles to implicitly model complex dialogue flows and pose high-quality instructions. In this paper, we take inspiration from the cognitive abilities inherent in human learning and propose the explicit modeling of complex dialogue flows through instructional strategy reuse. Specifically, we first induce high-level strategies from various real instruction dialogues. These strategies are applied to new dialogue scenarios deductively, where the instructional strategies facilitate high-quality instructions. Experimental results show that our method can generate diverse, in-depth, and insightful instructions for a given dialogue history. The constructed multi-turn instructional dialogues can outperform competitive baselines on the downstream chat model.

Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues

To handle the vast amounts of qualitative data produced in corporate climate communication, stakeholders increasingly rely on Retrieval Augmented Generation (RAG) systems. However, a significant gap remains in evaluating domain-specific information retrieval -- the basis for answer generation. To address this challenge, this work simulates the typical tasks of a sustainability analyst by examining 30 sustainability reports with 16 detailed climate-related questions. As a result, we obtain a dataset with over 8.5K unique question-source-answer pairs labeled by different levels of relevance. Furthermore, we develop a use case with the dataset to investigate the integration of expert knowledge into information retrieval with embeddings. Although we show that incorporating expert knowledge works, we also outline the critical limitations of embeddings in knowledge-intensive downstream domains like climate change communication.

ClimRetrieve: A Benchmarking Dataset for Information Retrieval from Corporate Climate Disclosures

We develop quantum RNNs with cells based on Parametrised Quantum Circuits (PQCs). PQCs can provide a form of hybrid quantum-classical computation where the input and the output is in the form of classical data. The previous "hidden" state is the quantum state from the previous time-step, and an angle encoding is used to define a (non-linear) mapping from a classical word embedding into the quantum Hilbert space. Measurements of the quantum state provide classical statistics which are used for classification. We report results which are competitive with various RNN baselines on the Rotten Tomatoes dataset, as well as emulator results which demonstrate the feasibility of running such models on quantum hardware.

Quantum Recurrent Architectures for Text Classification

Knowledge distillation (KD) is known as a promising solution to compress large language models (LLMs) via transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the output distributions of the two models so that more knowledge can be transferred. However, in the current white-box KD framework, the output distributions are from the respective output spaces of the two models, using their own prediction heads. We argue that the space discrepancy will lead to low similarity between the teacher model and the student model on both representation and distribution levels. Furthermore, this discrepancy also hinders the KD process between models with different vocabularies, which is common for current LLMs. To address these issues, we propose a dual-space knowledge distillation (DSKD) framework that unifies the output spaces of the two models for KD. On the basis of DSKD, we further develop a cross-model attention mechanism, which can automatically align the representations of the two models with different vocabularies. Thus, our framework is not only compatible with various distance functions for KD (e.g., KL divergence) like the current framework, but also supports KD between any two LLMs regardless of their vocabularies. Experiments on task-agnostic instruction-following benchmarks show that DSKD significantly outperforms the current white-box KD framework with various distance functions, and also surpasses existing KD methods for LLMs with different vocabularies.

Premium content

BaitAttack: Alleviating Intention Shift in Jailbreak Attacks via Adaptive Bait Crafting

Downloads

Next from EMNLP 2024

LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-Training

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES