EMNLP 2024 论文列表

Multimodal Large Language Models (MLLMs) have shown promising results in various tasks, but their ability to perceive the visual world with deep, hierarchical understanding similar to humans remains uncertain. To address this gap, we introduce CONSTRUCTURE, a novel concept-level benchmark to assess MLLMs’ hierarchical concept understanding and reasoning abilities. Our goal is to evaluate MLLMs across four key aspects: 1) Understanding atomic concepts at different levels of abstraction; 2) Performing upward abstraction reasoning across concepts; 3) Achieving downward concretization reasoning across concepts; and 4) Conducting multi-hop reasoning between sibling or common ancestor concepts. Our findings indicate that even state-of-the-art multimodal models struggle with concept structure reasoning (e.g., GPT-4o averages a score of 62.1%). We summarize key findings of MLLMs in concept structure reasoning evaluation. Morever, we provide key insights from experiments using CoT prompting and fine-tuning to enhance their abilities.

Complex logical reasoning over knowledge graphs lies at the heart of many semantic downstream applications and thus has been extensively explored in recent years. However, nearly all of them overlook the rich semantics of numerical entities (e.g., magnitude, unit, and distribution) and are simply treated as common entities, or even directly removed. It may severely hinder the performance of answering queries involving numerical comparison or numerical computation. To address this issue, we propose the Complex Number and Entity Query model (CNEQ), which comprises a Number-Entity Predictor and an Entity Filter. The Number-Entity Predictor can independently learn the structural and semantic features of entities and numerical values, thereby enabling better prediction of entities as well as numerical values. The Entity Filter can compare or calculate numerical values to filter out entities that meet certain numerical constraints. To evaluate our model, we generated a variety of multi-hop complex logical queries including numerical values on three widely-used Knowledge Graphs: FB15K, DB15K, and YAGO15K. Experimental results demonstrate that CNEQ achieves state-of-the-art results.

Large Language Models (LLMs) excel in diverse tasks but often underperform in specialized fields due to limited domain-specific or proprietary corpus. Continual pre-training (CPT) enhances LLM capabilities by imbuing new domain-specific or proprietary knowledge while replaying general corpus to prevent catastrophic forgetting. The data mixture ratio of general corpus and domain-specific corpus, however, has been chosen heuristically, leading to sub-optimal training efficiency in practice. In this context, we attempt to re-visit the scaling behavior of LLMs under the hood of CPT, and discover a power-law relationship between loss, mixture ratio, and training tokens scale. We formalize the trade-off between general and domain-specific capabilities, leading to a well-defined Critical Mixture Ratio (CMR) of general and domain data. By striking the balance, CMR maintains the model’s general ability and achieves the desired domain transfer, ensuring the highest utilization of available resources. Considering the balance between efficiency and effectiveness, CMR can be regarded as the optimal mixture ratio. Through extensive experiments, we ascertain the predictability of CMR, propose CMR scaling law and have substantiated its generalization. These findings offer practical guidelines for optimizing LLM training in specialized domains, ensuring both general and domain-specific performance while efficiently managing training resources.

Text detoxification aims to minimize the risk of language models producing toxic content. Existing detoxification methods of directly constraining the model output or further training the model on the non-toxic corpus fail to achieve a decent balance between detoxification effectiveness and generation quality. This issue stems from the neglect of constrain imposed by the context since language models are designed to generate output that closely matches the context while detoxification methods endeavor to ensure the safety of the output even if it semantically deviates from the context. In view of this, we introduce a Context-aware Model self-Detoxification (CMD) framework that pays attention to both the context and the detoxification process, i.e., first detoxifying the context and then making the language model generate along the safe context. Specifically, CMD framework involves two phases: utilizing language models to synthesize data and applying these data for training. We also introduce a toxic contrastive loss that encourages the model generation away from the negative toxic samples. Experiments on various LLMs have verified the effectiveness of our MSD framework, which can yield the best performance compared to baselines.

Developing Large Language Models (LLMs) with robust long-context capabilities has been the recent research focus, resulting in the emergence of long-context LLMs proficient in Chinese. However, the evaluation of these models remains underdeveloped due to a lack of benchmarks. To address this gap, we present CLongEval, a comprehensive Chinese benchmark for evaluating long-context LLMs. CLongEval is characterized by three key features: (1) Sufficient data volume, comprising 7 distinct tasks and 7,267 examples; (2) Broad applicability, accommodating to models with context windows size from 1K to 100K; (3) High quality, with over 2,000 manually annotated question-answer pairs in addition to the automatically constructed labels. With CLongEval, we undertake a comprehensive assessment of 6 open-source long-context LLMs and 2 leading commercial counterparts that feature both long-context abilities and proficiency in Chinese. We also provide in-depth analysis based on the empirical results, trying to shed light on the critical capabilities that present challenges in long-context settings. The dataset, evaluation scripts, and model outputs will be released.

Causal reasoning is a cornerstone of how humans interpret the world. To model and reason about causality, causal graphs offer a concise yet effective solution. Given the impressive advancements in language models, a crucial question arises: can they really understand causal graphs? To this end, we pioneer an investigation into language models’ understanding of causal graphs. Specifically, we develop a framework to define causal graph understanding, by assessing language models’ behaviors through four practical criteria derived from diverse disciplines (e.g., philosophy and psychology). We then develop CLEAR, a novel benchmark that defines three complexity levels and encompasses 20 causal graph-based tasks across these levels. Finally, based on our framework and benchmark, we conduct extensive experiments on six leading language models and summarize five empirical findings. Our results indicate that while language models demonstrate a preliminary understanding of causal graphs, significant potential for improvement remains.

Long sequence modeling has gained broad interest as large language models (LLMs) continue to advance. Recent research has identified that a large portion of hidden states within the key-value caches of Transformer models can be discarded (also termed evicted) withoutaffecting the perplexity performance in generating long sequences. However, we show that these methods, despite preserving perplexity performance, often drop information that is important for solving downstream tasks, a problem which we call information neglect. To address this issue, we introduce Chunked Instruction-aware State Eviction (CItruS), a novel modeling technique that integrates the attention preferences useful for a downstream task into the eviction process of hidden states. In addition, we design a method for chunked sequence processing to further improve efficiency. Our training-free method exhibits superior performance on long sequence comprehension and retrieval tasks over several strong baselines under the same memory budget, while preserving language modeling perplexity. The code and data have been released at https://github.com/ybai-nlp/CItruS.

Characters are integral to long-form narratives, but are poorly understood by existing story analysis and generation systems. While prior work has simplified characters via graph-based methods and brief character descriptions, we aim to better tackle the problem of representing complex characters by taking inspiration from advice given to professional writers. We propose CHIRON, a new ‘character sheet’ based representation that organizes and filters textual information about characters. We construct CHIRON sheets in two steps: a Generation Module that prompts an LLM for character information via question-answering and a Validation Module that uses automated reasoning and a domain-specific entailment model to eliminate false facts about a character. We validate CHIRON via the downstream task of masked-character prediction, where our experiments show CHIRON is better and more flexible than comparable summary-based baselines. We also show that metrics derived from CHIRON can be used to automatically infer character-centricity in stories, and that these metrics align with human judgments.

In this paper, we study how open-source large language models (LLMs) can be effectively deployed for improving query rewriting in conversational search, especially for ambiguous queries. We introduce CHIQ, a two-step method that leverages the capabilities of LLMs to resolve ambiguities in the conversation history before query rewriting. This approach contrasts with prior studies that predominantly use closed-source LLMs to directly generate search queries from conversation history. We demonstrate on five well-established benchmarks that CHIQ leads to state-of-the-art results across most settings, showing highly competitive performances with systems leveraging closed-source LLMs. Our study provides a first step towards leveraging open-source LLMs in conversational search, as a competitive alternative to the prevailing reliance on commercial LLMs. Data, models, and source code will be publicly available upon acceptance at https://github.com/fengranMark/CHIQ.

Deploying large language models (LLMs) on edge devices presents significant challenges due to the substantial computational overhead and memory requirements. Activation sparsification can mitigate these resource challenges by reducing the number of activated neurons during inference. Existing methods typically employ thresholding-based sparsification based on the statistics of activation tensors. However, they do not model the impact of activation sparsification on performance, resulting in suboptimal performance degradation. To address the limitations, this paper reformulates the activation sparsification problem to explicitly capture the relationship between activation sparsity and model performance. Then, this paper proposes CHESS, a general activation sparsification approach via CHannel-wise thrEsholding and Selective Sparsification. First, channel-wise thresholding assigns a unique threshold to each activation channel in the feed-forward network (FFN) layers. Then, selective sparsification involves applying thresholding-based activation sparsification to specific layers within the attention modules. Finally, we detail the implementation of sparse kernels to accelerate LLM inference. Experimental results demonstrate that the proposed CHESS achieves lower performance degradation over eight downstream tasks while activating fewer parameters than existing methods, thus speeding up the LLM inference by up to 1.27x.

Ambiguity is an inherent feature of language, whose management is crucial for effective communication and collaboration. This is particularly true for Chinese, a language with extensive lexical-morphemic ambiguity. Despite the wide use of large language models (LLMs) in numerous domains and their growing proficiency in Chinese, there is a notable lack of datasets to thoroughly evaluate LLMs’ ability to handle ambiguity in Chinese. To bridge this gap, we introduce the CHAmbi dataset, a specialized Chinese multi-label disambiguation dataset formatted in Natural Language Inference. It comprises 4,991 pairs of premises and hypotheses, including 824 examples featuring a wide range of ambiguities. In addition to the dataset, we develop a series of tests and conduct an extensive evaluation of pre-trained LLMs’ proficiency in identifying and resolving ambiguity in the Chinese language. Our findings reveal that GPT-4 consistently delivers commendable performance across various evaluative measures, albeit with limitations in robustness. The performances of other LLMs, however, demonstrate variability in handling ambiguity-related tasks, underscoring the complexity of such tasks in the context of Chinese. The overall results highlight the challenge of ambiguity handling for current LLMs and underscore the imperative need for further enhancement in LLM capabilities for effective ambiguity resolution in the Chinese language.

With the growing integration of AI in daily life, ensuring the robustness of systems to inference-time attacks is crucial. Among the approaches for certifying robustness to such adversarial examples, randomized smoothing has emerged as highly promising due to its nature as a wrapper around arbitrary black-box models. Previous work on randomized smoothing in natural language processing has primarily focused on specific subsets of edit distance operations, such as synonym substitution or word insertion, without exploring the certification of all edit operations. In this paper, we adapt Randomized Deletion (Huang et al., 2023) and propose, CERTified Edit Distance defense (CERT-ED) for natural language classification. Through comprehensive experiments, we demonstrate that CERT-ED outperforms the existing Hamming distance method RanMASK (Zeng et al., 2023) in 4 out of 5 datasets in terms of both accuracy and the cardinality of the certificate. By covering various threat models, including 5 direct and 5 transfer attacks, our method improves empirical robustness in 38 out of 50 settings.

Causal reasoning is fundamental to human intelligence and crucial for effective decision-making in real-world environments. Despite recent advancements in large vision-language models (LVLMs), their ability to comprehend causality remains unclear. Previous work typically focuses on commonsense causality between events and/or actions, which is insufficient for applications like embodied agents and lacks the explicitly defined causal graphs required for formal causal reasoning. To overcome these limitations, we introduce a fine-grained and unified definition of causality involving interactions between humans and/or objects. Building on the definition, we construct a novel dataset, CELLO, consisting of 14,094 causal questions across all four levels of causality: discovery, association, intervention, and counterfactual. This dataset surpasses traditional commonsense causality by including explicit causal graphs that detail the interactions between humans and objects. Extensive experiments on CELLO reveal that current LVLMs still struggle with causal reasoning tasks, but they can benefit significantly from our proposed CELLO-CoT, a causally inspired chain-of-thought prompting strategy. Both quantitative and qualitative analyses from this study provide valuable insights for future research. Our project page is at https://github.com/OpenCausaLab/CELLO.

Detecting out-of-distribution (OOD) samples is crucial for ensuring the safety and robustness of models deployed in real-world scenarios. While most studies on OOD detection focus on fine-tuned models trained on in-distribution (ID) data, detecting OOD in pre-trained models is also important due to computational limitations and the widespread use of open-source pre-trained models. However, in the same domain shift setting, the OOD detection performance of pre-trained models is insufficient because both ID and OOD samples originate from the same domain, leading to a high overlap in their embeddings. To address this issue, we introduce a new method called CED, a training-free OOD detection technique designed to enhance the distinction between ID and OOD datasets. We theoretically validate that specific auxiliary and oracle samples that satisfy certain conditions improve this distinction. Motivated by our theoretical analysis, CED enhances the differentiation by utilizing these specially designed auxiliary and oracle samples. As a result, CED significantly improves the ability of pre-trained models to distinguish between ID and OOD samples in text classification and hallucination detection tasks. Furthermore, we verify that CED is a plug-and-play method compatible with various backbone networks, such as RoBERTa, Llama, and OpenAI Embedding.

This paper introduces the Chinese Essay Argument Mining Corpus (CEAMC), a manually annotated dataset designed for argument component classification on multiple levels of granularity. Existing argument component types in education remain simplistic and isolated, failing to encapsulate the complete argument information. Originating from authentic examination settings, CEAMC categorizes argument components into 4 coarse-grained and 10 fine-grained delineations, surpassing previous simple representations to capture the subtle nuances of argumentation in the real world, thus meeting the needs of complex and diverse argumentative scenarios. Our contributions include the development of CEAMC, the establishment of baselines for further research, and a thorough exploration of the performance of Large Language Models (LLMs) on CEAMC. The results indicate that our CEAMC can serve as a challenging benchmark for the development of argument analysis in education.

It is well-known that language models are biased; they have patchy knowledge of countries and cultures that are poorly represented in their training data. We introduce CAVA, a visualization tool for identifying and analyzing country-specific biases in language models.Our tool allows users to identify whether a language model successful captures the perspectives of people of different nationalities. The tool supports analysis of both longform and multiple-choice models responses and comparisons between models.Our open-source code easily allows users to upload any country-based language model generations they wish to analyze.To showcase CAVA’s efficacy, we present a case study analyzing how several popular language models answer survey questions from the World Values Survey.

The limited availability of psychologists necessitates efficient identification of individuals requiring urgent mental healthcare. This study explores the use of Natural Language Processing (NLP) pipelines to analyze text data from online mental health forums used for consultations. By analyzing forum posts, these pipelines can flag users who may require immediate professional attention. A crucial challenge in this domain is data privacy and scarcity. To address this, we propose utilizing readily available curricular texts used in institutes specializing in mental health for pre-training the NLP pipelines. This helps us mimic the training process of a psychologist. Our work presents CASE-BERT that flags potential mental health disorders based on forum text. CASE-BERT demonstrates superior performance compared to existing methods, achieving an f1 score of 0.91 for Depression and 0.88 for Anxiety, two of the most commonly reported mental health disorders. Our code and data are publicly available.

The increasing availability of multimodal data from electronic health records (EHR) has paved the way for deep learning methods to improve diagnosis accuracy. However, deep learning models are data-driven, requiring large-scale datasets to achieve high generalizability. Inspired by how human experts leverage reasoning for medical diagnosis, we propose CARER, a novel health risk prediction framework, that enhances deep learning models with clinical rationales derived from medically proficient Large Language Models (LLMs). In addition, we provide a cross-view alignment loss which aligns the “local” view from the patient’s health status with the “global” view from the external LLM’s clinical reasoning to boost the mutual feature learning. Through extensive experiments on two predictive tasks using two popular EHR datasets, our CARER’s significantly exceeds the performance of state-of-the-art models by up to 11.2%, especially in improving data efficiency and generalizability. Our code is available at https://github.com/tuandung2812/CARER-EMNLP-2024

The development of tools and techniques to analyze and extract organizations’ data habits from privacy policies are critical for scalable regulatory compliance audits. Unfortunately, these tools are becoming increasingly limited in their ability to identify compliance issues and fixes. After all, most were developed using regulation-agnostic datasets of annotated privacy policies obtained from a time before the introduction of landmark privacy regulations such as EU’s GDPR and California’s CCPA. In this paper, we describe the first open regulation-aware dataset of expert-annotated privacy policies, C3PA (CCPA Privacy Policy Provision Annotations), aimed to address this challenge. C3PA contains over 48K expert-labeled privacy policy text segments associated with responses to CCPA-specific disclosure mandates from 411 unique organizations. We demonstrate that the C3PA dataset is uniquely suited for aiding automated audits of compliance with CCPA-related disclosure mandates.