EMNLP 2024 Papers

Extracting and aggregating information from clinical trial registries could provide invaluable insights into the drug development landscape and advance the treatment of neurologic diseases. However, achieving this at scale is hampered by the volume of available data and the lack of an annotated corpus to assist in the development of automation tools. Thus, we introduce NeuroTrialNER, a new and fully open corpus for named entity recognition (NER). It comprises 1093 clinical trial summaries sourced from ClinicalTrials.gov, annotated for neurological diseases, therapeutic interventions, and control treatments. We describe our data collection process and the corpus in detail. We demonstrate its utility for NER using large language models and achieve a close-to-human performance. By bridging the gap in data resources, we hope to foster the development of text processing tools that help researchers navigate clinical trials data more easily.

Recent advances in neural topic models have concentrated on two primary directions: the integration of the inference network (encoder) with a pre-trained language model (PLM) and the modeling of the relationship between words and topics in the generative model (decoder). However, the use of large PLMs significantly increases inference costs, making them less practical for situations requiring low inference times. Furthermore, it is crucial to simultaneously model the relationships between topics and words as well as the interrelationships among topics themselves. In this work, we propose a novel framework called NeuroMax (**Neur**al T**o**pic Model with **Max**imizing Mutual Information with Pretrained Language Model and Group Topic Regularization) to address these challenges. NeuroMax maximizes the mutual information between the topic representation obtained from the encoder in neural topic models and the representation derived from the PLM. Additionally, NeuroMax employs optimal transport to learn the relationships between topics by analyzing how information is transported among them. Experimental results indicate that NeuroMax reduces inference time, generates more coherent topics and topic groups, and produces more representative document embeddings, thereby enhancing performance on downstream tasks.

Gboard Decoder produces suggestions by looking for paths that best match input touch points on the context aware search space, which is backed by the language Finite State Transducers (FST). The language FST is currently an N-gram language model (LM). However, N-gram LMs, limited in context length, are known to have sparsity problem under device model size constraint. In this paper, we propose Neural Search Space which substitutes the N-gram LM with a Neural Network LM (NN-LM) and dynamically constructs the search space during decoding. Specifically, we integrate the long range context awareness of NN-LM into the search space by converting its outputs given context, into the language FST at runtime. This involves language FST structure redesign, pruning strategies tuning, and data structure optimizations. Online experiments demonstrate improved quality results, reducing Words Modified Ratio by [0.26%, 1.19%] on various locales with acceptable latency increases. This work opens new avenues for further improving keyboard decoding quality by enhancing neural LM more directly.

Large Language Models (LLMs) have sparked substantial interest and debate concerning their potential emergence of Theory of Mind (ToM) ability. Theory of mind evaluations currently focuses on testing models using machine-generated data or game settings prone to shortcuts and spurious correlations, which lacks evaluation of machine ToM ability in real-world human interaction scenarios. This poses a pressing demand to develop new real-world scenario benchmarks. We introduce NegotiationToM, a new benchmark designed to stress-test machine ToM in real-world negotiation surrounding covered multi-dimensional mental states (i.e., desires, beliefs, and intentions). Our benchmark builds upon the Belief-Desire-Intention (BDI) agent modeling theory and conducts the necessary empirical experiments to evaluate large language models. Our findings demonstrate that NegotiationToM is challenging for state-of-the-art LLMs, as they consistently perform significantly worse than humans, even when employing the chain-of-thought (CoT) method.

Large language models (LLMs) have revolutionized the role of AI, yet pose potential social risks. To steer LLMs towards human preference, alignment technologies have been introduced and gained increasing attention. Nevertheless, existing methods heavily rely on high-quality positive-negative training pairs, suffering from noisy positive responses that are barely distinguishable from negative ones. Given recent LLMs’ proficiency in generating helpful responses, this work pivots towards a new research question: **can we achieve alignment using solely human-annotated negative samples, preserving helpfulness while reducing harmfulness?** For this purpose, we propose Distributional Dispreference Optimization (D2O), which maximizes the discrepancy between dispreferred responses and the generated non-negative ones. In this way, D2O effectively eschews harmful information without incorporating noisy positive samples, while avoiding collapse using self-generated responses as anchors. We demonstrate that D2O can be regarded as learning a distributional preference model reflecting human dispreference against negative responses, which is theoretically an upper bound of the instance-level DPO. Extensive experiments manifest that our method achieves comparable generation quality and surpasses the latest strong baselines in producing less harmful and more informative responses with better training stability and faster convergence.

Large Language Models (LLMs) have revolutionized open-domain dialogue agents but encounter challenges in multi-character role-playing (MCRP) scenarios. To address the issue, we present Neeko, an innovative framework designed for efficient multiple characters imitation. Neeko employs a dynamic low-rank adapter (LoRA) strategy, enabling it to adapt seamlessly to diverse characters. Our framework breaks down the role-playing process into agent pre-training, multiple characters playing, and character incremental learning, effectively handling both seen and unseen roles. This dynamic approach, coupled with distinct LoRA blocks for each character, enhances Neeko’s adaptability to unique attributes, personalities, and speaking patterns. As a result, Neeko demonstrates superior performance in MCRP over most existing methods, offering more engaging and versatile user interaction experiences.

When engaging in collaborative tasks, humans efficiently exploit the semantic structure of a conversation to optimize verbal and nonverbal interactions. But in recent “language to code” or “language to action” models, this information is lacking. We show how incorporating the prior discourse and nonlinguistic context of a conversation situated in a nonlinguistic environment can improve the “language to action” component of such interactions. We finetune an LLM to predict actions based on prior context; our model, Nebula, doubles the net-action F1 score over the baseline on this task of Jayannavar et al. (2020). We also investigate our model’s ability to construct shapes and understand location descriptions using a synthetic dataset.

Multimodal models leverage large-scale pretraining to achieve strong but still imperfect performance on tasks such as image captioning, visual question answering, and cross-modal retrieval. In this paper, we present a simple and efficient method for correcting errors in trained contrastive image-text retrieval models with no additional training, called Nearest Neighbor Normalization (NNN). We show an improvement on retrieval metrics in both text retrieval and image retrieval for all of the contrastive models that we tested (CLIP, BLIP, ALBEF, SigLIP, BEiT) and for both of the datasets that we used (MS-COCO and Flickr30k). NNN requires a reference database, but does not require any training on this database, and can even increase the retrieval accuracy of a model after finetuning.

Language models (LMs), despite their advances, often depend on spurious correlations, undermining their accuracy and generalizability. This study addresses the overlooked impact of subtler, more complex shortcuts that compromise model reliability beyond oversimplified shortcuts. We introduce a comprehensive benchmark that categorizes shortcuts into occurrence, style, and concept, aiming to explore the nuanced ways in which these shortcuts influence the performance of LMs. Through extensive experiments across traditional LMs, large language models, and state-of-the-art robust models, our research systematically investigates models’ resilience and susceptibilities to sophisticated shortcuts. Our benchmark and code can be found at: https://github.com/yuqing-zhou/shortcut-learning-in-text-classification.

This study presents a novel evaluation framework for the Vision-Language Navigation (VLN) task. It aims to diagnose current models for various instruction categories at a finer-grained level. The framework is structured around the context-free grammar (CFG) of the task. The CFG serves as the basis for the problem decomposition and the core premise of the instruction categories design. We propose a semi-automatic method for CFG construction with the help of Large-Language Models (LLMs). Then, we induct and generate data spanning five principal instruction categories (i.e. direction change, landmark recognition, region recognition, vertical movement, and numerical comprehension). Our analysis of different models reveals notable performance discrepancies and recurrent issues. The stagnation of numerical comprehension, heavy selective biases over directional concepts, and other interesting findings contribute to the development of future language-guided navigation systems. The project is now available at https://zehao-wang.github.io/navnuances.

The correct specification of reward models is a well-known challenge in reinforcement learning.Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values.Reinforcement learning from human feedback is a successful technique that can mitigate such issues, however, the collection of human feedback can be laborious.Recent works have solicited feedback from pre-trained large language models rather than humans to reduce or eliminate human effort, however, these approaches yield poor performance in the presence of hallucination and other errors.This paper studies the advantages and limitations of reinforcement learning from large language model feedback and proposes a simple yet effective method for soliciting and applying feedback as a potential-based shaping function.We theoretically show that inconsistent rankings – which approximate ranking errors – lead to uninformative rewards with our approach. Our method empirically improves convergence speed and policy returns over commonly used baselines even with significant ranking errors, and eliminates the need for complex post-processing of reward functions.

In this work we present a novel task of understanding unintentional human activities in videos. We formalize this problem as a reasoning task under zero-shot scenario, where given a video of an unintentional activity we want to know why it transitioned from intentional to unintentional. We first evaluate the effectiveness of current state-of-the-art Large Multimodal Models on this reasoning task and observe that they suffer from hallucination. We further propose a novel prompting technique, termed as Dream of Thoughts (DoT), which allows the model to navigate through hallucinated thoughts to achieve better reasoning. To evaluate the performance on this task, we also introduce three different specialized metrics designed to quantify the models reasoning capability. We perform our experiments on three datasets, OOPs, UCF-Crimes, and ReUAct, and our findings show that DOT prompting technique is able to outperform standard prompting, while minimizing hallucinations.

Temporal knowledge graph (TKG) reasoning aims to predict missing facts based on a given history. Most of the existing methods unifiedly model the evolution process of different events and ignore their inherent asynchronous characteristics, resulting in suboptimal performance. To tackle this challenge, we propose a Natural Evolution-based Dual-level Aggregation framework (NEDA) for TKG reasoning. Specifically, we design a natural division strategy to group TKGs into different patches according to the occurrence of a given target entity. Then, we present a dual-level aggregation scheme to extract local representations from information within patches and then aggregate these representations with adaptive weights as the final entity representations. By assigning varying weights to different patches, this aggregation scheme can incorporate the asynchronous characteristics of event evolution for representation computation, thus enhancing prediction performance. Extensive experiments demonstrate the significant improvement of our proposed model.

Chain of thought (CoT) is a reasoning framework that can enhance the performance of large language models (LLMs) on complex inference tasks. In particular, among various studies related to CoT, multi-path inference stands out as a simple yet effective improvement. However, there is no optimal setting for the number of inference paths. Therefore, we have to increase the number of inference paths to obtain better results, which in turn increases the inference cost. To address this limitation, we can utilize question-related role templates to guide LLMs into relevant roles, thereby increasing the possibility of correct inferences for each path and further reducing dependence on the number of inference paths while improving reasoning accuracy. However, placing LLMs into specific roles may reduce their reasoning diversity and performance on a few tasks where role dependence is low. To alleviate the excessive immersion of the LLM into a specific role, we propose Nash CoT by constructing a competitive system on each path that balances the generation from role-specific LLMs’ and the general LLMs’ generation, thereby ensuring both effective role adoption and diversity in LLM generation further maintaining the performance of multi-path inference while reducing the requirement of the number of inference paths. We evaluate Nash CoT across various inference tasks, including Arabic Reasoning, Commonsense Question Answering, and Symbolic Inference, achieving results that are comparable to or better than those of multi-path CoT with the equal number of inference paths.

Reasoning about time and temporal relations is an integral aspect of human cognition, essential for perceiving the world and navigating our experiences. Though large language models (LLMs) have demonstrated impressive performance in many reasoning tasks, temporal reasoning remains challenging due to its intrinsic complexity. In this work, we first study an essential task of temporal reasoning—temporal graph generation, to unveil LLMs’ inherent, global reasoning capabilities. We show that this task presents great challenges even for the most powerful LLMs, such as GPT-3.5/4. We also notice a significant performance gap by small models (< 10B) that lag behind LLMs by 50%. Next, we study how to close this gap with a budget constraint, e.g., not using model finetuning. We propose a new prompting technique tailored for temporal reasoning, Narrative-of-Thought (NoT), that first converts the events set to a Python class, then prompts a small model to generate a temporally grounded narrative, guiding the final generation of a temporal graph. Extensive experiments showcase the efficacy of NoT in improving various metrics. Notably, NoT attains the highest F1 on the Schema-11 evaluation set, while securing an overall F1 on par with GPT-3.5. NoT also achieves the best structural similarity across the board, even compared with GPT-3.5/4.

Norwegian, spoken by only 5 million population, is under-representative within the most impressive breakthroughs in NLP tasks. To the best of our knowledge, there has not yet been a comprehensive evaluation of the existing language models (LMs) on Norwegian generation tasks during the article writing process. To fill this gap, we 1) compiled the existing Norwegian dataset and pre-trained 4 Norwegian Open Language Models varied from parameter scales and architectures, collectively called NorGLM; 2) introduced a comprehensive benchmark, NLEBench, for evaluating natural language generation capabilities in Norwegian, encompassing translation and human annotation. Based on the investigation, we find that: 1) the mainstream, English-dominated LM GPT-3.5 has limited capability in understanding the Norwegian context; 2) the increase in model parameter scales demonstrates limited impact on the performance of downstream tasks when the pre-training dataset is constrained in size; 3) smaller models also demonstrate the reasoning capability through Chain-of-Thought; 4) a multi-task dataset that includes synergy tasks can be used to verify the generalizability of LLMs on natural language understanding and, meanwhile, test the interconnectedness of these NLP tasks. We share our resources and code for reproducibility under a CC BY-NC 4.0 license.

Implicit Discourse Relation Recognition (IDRR) is an important task to classify the discourse relation sense between argument pairs without an explicit connective. Recently, prompt learning methods have demonstrated success in IDRR. However, prior work primarily transform IDRR into a connective-cloze task based on the masked language model (MLM), which limits the predicted connective to one single token. Also, they fail to fully exploit critical semantic features shared among various forms of templates. In this paper, we propose NCPrompt, an NSP-based prompt learning and Contrastive learning method for IDRR. Specifically, we transform the IDRR task into a next sentence prediction (NSP) task, which can allow various-length answer connectives and enlarge the construction of the verbalizer for prompt-learning methods. Also, we notice that various prompt templates naturally constitute positive samples applied for self-supervised contrastive learning. And the usage of NSP naturally creates hard negative samples by introducing different candidate connectives between the same example. To our knowledge, we are the first to combine self-supervised contrastive learning with prompt learning to obtain high-quality semantic representations. Experiments on the PDTB 3.0 corpus have demonstrated the effectiveness and superiority of our model.

Entity alignment (EA) aims to find equivalent entities between two Knowledge Graphs. Existing embedding-based EA methods usually encode entities as embeddings, triples as embeddings’ constraint and learn to align the embeddings. However, the details of the underlying logical inference steps among the alignment process are usually omitted, resulting in inadequate inference process. In this paper, we introduce NALA, an entity alignment method that captures three types of logical inference paths with Non-Axiomatic Logic (NAL). Type 1&2 align the entity pairs and type 3 aligns relations. NALA iteratively aligns entities and relations by integrating the conclusions of the inference paths. Our method is logically interpretable and extensible by introducing NAL, and thus suitable for various EA settings. Experimental results show that NALA outperforms state-of-the-art methods in terms of Hits@1, achieving 0.98+ on all three datasets of DBP15K with both supervised and unsupervised settings. We offer a pioneering in-depth analysis of the fundamental principles of entity alignment, approaching the subject from a unified and logical perspective. Our code is available at https://github.com/13998151318/NALA.

In this paper, we address the data scarcity problem in automatic data-driven glossing for low-resource languages by coordinating multiple sources of linguistic expertise. We enhance models by incorporating both token-level and sentence-level translations, utilizing the extensive linguistic capabilities of modern LLMs, and incorporating available dictionary resources. Our enhancements lead to an average absolute improvement of 5%-points in word-level accuracy over the previous state of the art on a typologically diverse dataset spanning six low-resource languages. The improvements are particularly noticeable for the lowest-resourced language Gitksan, where we achieve a 10%-point improvement. Furthermore, in a simulated ultra-low resource setting for the same six languages, training on fewer than 100 glossed sentences, we establish an average 10%-point improvement in word-level accuracy over the previous state-of-the-art system.