United States

LLMs acquire knowledge from massive data snapshots collected at different timestamps. Their knowledge is then commonly evaluated using static benchmarks. However, factual knowledge is generally subject to time-sensitive changes, and static benchmarks cannot address those cases. We present an approach to dynamically evaluate the knowledge in LLMs and their time-sensitiveness against Wikidata, a publicly available up-to-date knowledge graph. We evaluate the time-sensitive knowledge in twenty-four private and open-source LLMs, as well as the effectiveness of four editing methods in updating the outdated facts. Our results show that 1) outdatedness is a critical problem across state-of-the-art LLMs; 2) LLMs output inconsistent answers when prompted with slight variations of the question prompt; and 3) the performance of the state-of-the-art knowledge editing algorithms is very limited, as they can not reduce the cases of outdatedness and output inconsistency.

EMNLP 2024

DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs

task-oriented-dialogue

reward design

reinforcement learning

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.

Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in natural language processing. In particular, large language models (LLMs) can hardly produce written works at the level of human experts due to the extremely high complexity of literature writing. In this paper, we present HoLLMwood, an automated framework for unleashing the creativity of LLMs and exploring their potential in screenwriting, which is a highly demanding task. Mimicking the human creative process, we assign LLMs to different roles involved in the real-world scenario. In addition to the common practice of treating LLMs as $Writer$, we also apply LLMs as $Editor$, who is responsible for providing feedback and revision advice to $Writer$. Besides, to enrich the characters and deepen the plots, we introduce a role-playing mechanism and adopt LLMs as $Actors$ that can communicate and interact with each other. Evaluations on automatically generated screenplays show that HoLLMwood substantially outperforms strong baselines in terms of coherence, relevance, interestingness and overall quality.

HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing

Recent advancements in educational platforms have emphasized the importance of personalized education. Accurately estimating question difficulty based on the ability of the student group is essential for personalized question recommendations. Several studies have focused on predicting question difficulty using student question-solving records or textual information about the questions. However, these approaches require a large amount of student question-solving records and fail to account for the subjective difficulties perceived by different student groups. To address these limitations, we propose the LLaSA framework that utilizes large language models to represent students at various levels. Our proposed method, LLaSA and the zero-shot LLaSA, can estimate question difficulty both with and without students’ question-solving records. In evaluations on the DBE-KT22 and ASSISTMents 2005–2006 benchmarks, the zero-shot LLaSA demonstrated a performance comparable to those of strong baseline models even without any training. When evaluated using the classification method, LLaSA outperformed the baseline models, achieving state-of-the-art performance. In addition, the zero-shot LLaSA showed a high correlation with the regressed IRT curve when compared to question difficulty derived from students’ question-solving records, highlighting its potential for real-world applications.

Large Language Models are Students at Various Levels: Zero-shot Question Difficulty Estimation

When large language models (LLMs) surpass human capabilities, supervising them effectively becomes difficult. \textit{Weak-to-strong learning}, where a less capable model enhances a stronger one, proves valuable in this context. Yet, the efficacy of this paradigm for complex reasoning tasks is still unexplored. In this paper, we introduce a progressive weak-to-strong reasoning framework that enables the strong model to autonomously refine its training data, maximizing the use of weak signals and unlocking its latent abilities. This framework begins with supervised fine-tuning on a selective small but high-quality dataset, followed by preference optimization on contrastive samples identified by the strong model itself. Experiments on the GSM8K and MATH datasets verify that our method can effectively improve the reasoning capabilities of Llama2-70b using three separate weak models. This work paves the way for a more scalable and sophisticated strategy to enhance AI reasoning powers. All relevant code and resources are available in \url{https://github.com/GAIR-NLP/weak-to-strong-reasoning}.

Weak-to-Strong Reasoning

Foundation Language Models (FLMs) such as BERT and its variants have achieved remarkable success in natural language processing. To date, the interpretability of FLMs has primarily relied on the attention weights in their self-attention layers. However, these attention weights only provide word-level interpretations, failing to capture higher-level structures, and are therefore lacking in readability and intuitiveness. 
To address this challenge, we first provide a formal definition of *conceptual interpretation* and then propose a variational Bayesian framework, dubbed VAriational Language Concept (VALC), to go beyond word-level interpretations and provide concept-level interpretations. Our theoretical analysis shows that our VALC finds the optimal language concepts to interpret FLM predictions. Empirical results on several real-world datasets show that our method can successfully provide conceptual interpretation for FLMs.

Variational Language Concepts for Interpreting Pretrained Language Models

Recent advances in Large Language Models (LLMs) have sparked wide interest in validating and comprehending the human-like cognitive-behavioral traits LLMs may capture and convey. These cognitive-behavioral traits include typically Attitudes, Opinions, Values (AOVs). However, measuring AOVs embedded within LLMs remains opaque, and different evaluation methods may yield different results. This has led to a lack of clarity on how different studies are related to each other and how they can be interpreted. This paper aims to bridge this gap by providing a comprehensive overview of recent works on the evaluation of AOVs in LLMs. Moreover, we survey related approaches in different stages of the evaluation pipeline in these works. By doing so, we address the potential and challenges with respect to understanding the model, human-AI alignment, and downstream application in social sciences. Finally, we provide practical insights into evaluation methods, model enhancement, and interdisciplinary collaboration, thereby contributing to the evolving landscape of evaluating AOVs in LLMs.

The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models

Though large language models (LLMs) achieve significant success in recent years, the hallucination issue remains a challenge, and numerous benchmarks are proposed for hallucination detection. Nevertheless, some of these benchmarks are not naturally generated by LLMs but are intentionally induced. Also, many merely focus on the factuality hallucination while ignoring the faithfulness hallucination. Additionally, although dialogue pattern is more widely utilized in the era of LLMs, current benchmarks only concentrate on sentence-level and passage-level hallucination. In this study, we propose DiaHalu, the first dedicated dialogue-level hallucination evaluation benchmark for LLMs to our knowledge. Initially, we integrate the collected topics into system prompts and facilitate a dialogue between two LLMs. Subsequently, we manually modify the contents that do not adhere to human language conventions and then have LLMs re-generate, simulating authentic human-machine interaction scenarios. Finally, professional scholars annotate all the samples in the dataset. DiaHalu covers four common multi-turn dialogue domains and five hallucination subtypes, extended from factuality and faithfulness hallucination. Experiments through some well-known LLMs and detection methods on the dataset show that DiaHalu is a challenging benchmark, holding significant value for further research.

DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models

Text-to-speech (TTS) systems that scale up the amount of training data have achieved significant improvements in zero-shot speech synthesis. However, these systems have certain limitations: they require a large amount of training data, which increases costs, and often overlook prosody similarity. To address these issues, we propose MultiVerse, a zero-shot multi-task TTS system that is able to perform TTS or speech style transfer in zero-shot and cross-lingual conditions. MultiVerse requires much less training data than traditional data-driven approaches. To ensure zero-shot performance even with limited data, we leverage source-filter theory-based disentanglement, utilizing the prompt for modeling filter-related and source-related representations. Additionally, to further enhance prosody similarity, we adopt a prosody modeling approach combining prompt-based autoregressive and non-autoregressive methods. Evaluations demonstrate the remarkable zero-shot multi-task TTS performance of MultiVerse and show that MultiVerse not only achieves zero-shot TTS performance comparable to data-driven TTS systems with much less data, but also significantly outperforms other zero-shot TTS systems trained with the same small amount of data. In particular, our novel prosody modeling technique significantly contributes to MultiVerse's ability to generate speech with high prosody similarity to the given prompts.

MultiVerse: Efficient and Expressive Zero-Shot Multi-Task Text-to-Speech

Low-rank adaptation (LoRA) has become the default approach to fine-tune large language models (LLMs) due to its significant reduction in trainable parameters. However, trainable parameter demand for LoRA increases with increasing model embedding dimensions, leading to high compute costs. Additionally, its backward updates require storing high-dimensional intermediate activations and optimizer states, demanding high peak GPU memory. 
In this paper, we introduce _LaMDA_, a novel approach to fine-tuning large language models, which leverages low-dimensional adaptation to achieve significant reductions in trainable parameters and peak GPU memory footprint. LaMDA freezes a first projection matrix (PMA) in the adaptation path while introducing a low-dimensional trainable square matrix, resulting in substantial reductions in trainable parameters and peak GPU memory usage. LaMDA gradually freezes a second projection matrix (PMB) during the early fine-tuning stages, reducing the compute cost associated with weight updates to enhance parameter efficiency further.
We also present an enhancement, LaMDA++, incorporating a "lite-weight" adaptive rank allocation for the LoRA path via normalized spectrum analysis of pre-trained model weights. We evaluate LaMDA/LaMDA++ across various tasks, including natural language understanding with the GLUE benchmark, text summarization, natural language generation, and complex reasoning on different LLMs.
Results show that LaMDA matches or surpasses the performance of existing alternatives while requiring up to **17.7$\times$** fewer parameter updates and up to **1.32$\times$** lower peak GPU memory usage during fine-tuning. Code will be publicly available at https://github.com/ArminAzizi98/LaMDA.

LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation

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

RL-based techniques can be employed to search for prompts that, when fed into a target language model, maximize a set of user-specified reward functions. However, in many target applications, the natural reward functions are in tension with one another -- for example, content preservation vs. style matching in style transfer tasks. Current techniques focus on maximizing the average of reward functions, which does not necessarily lead to prompts that achieve balance across rewards -- an issue that has been well-studied in the multi-objective and robust optimization literature. In this paper, we conduct an empirical comparison of several existing multi-objective optimization techniques adapted to this new setting: RL-based discrete prompt optimization. We compare two methods optimizing the volume of the Pareto reward surface and one method that chooses an update direction that benefits all rewards simultaneously. We evaluate performance on two NLP tasks: style transfer and machine translation, each using three competing reward functions. Our experiments demonstrate that multi-objective methods that directly optimize the volume of the Pareto reward surface perform better and achieve a better balance of all rewards than those that attempt to find monotonic update directions.

Premium content

DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs

Downloads

Next from EMNLP 2024

HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES