EMNLP 2024 Papers

In modern commercial systems, including Recommendation, Ranking, and E-Commerce platforms, there is a trend towards improving customer experiences by incorporating Personalization context as input into Large Language Models (LLM). However, LLMs often struggle to effectively parse and utilize sparse and complex personal context without additional processing or contextual enrichment, underscoring the need for more sophisticated context understanding mechanisms. In this work, we propose Guided Profile Generation (GPG), a general method designed to generate personal profiles in natural language. As is observed, intermediate guided profile generation enables LLMs to summarize, and extract the important, distinctive features from the personal context into concise, descriptive sentences, precisely tailoring their generation more closely to an individual’s unique habits and preferences. Our experimental results show that GPG improves LLM’s personalization ability across different tasks, for example, it increases 37% accuracy in predicting personal preference compared to directly feeding the LLMs with raw personal context.

Large Language Models (LLMs) have achieved notable success in commonsense reasoning tasks, benefiting from their extensive world knowledge acquired through extensive pretraining. While approaches like Chain-of-Thought (CoT) have shown promise in enhancing LLMs’ reasoning capabilities, mitigating the influence of inaccurate commonsense knowledge remains a challenge, particularly for small-scale LLMs (e.g., those with less than 10B parameters). In this work, we propose a novel method named Guided Knowledge Generation (GuideKG) to address these issues. It presents three advantages: (i) Employing LLMs to generate knowledge explanations and to automatically assign labels based on the probability of correct answers eliminates the need for costly manual annotation in subsequent training. (ii) Training a new module called the ‘Know-Filter’, which is used to evaluate knowledge, and we have introduced a new loss to enhance its performance. (iii) Evaluating the effectiveness of knowledge fragments at the sentence level and fusing them allows for precise control over the generation process of LLMs. We evaluate our GuideKG on small-scale LLMs and show that it outperforms all baselines on four widely-used commonsense reasoning benchmarks. Moreover, our experiments reveal that, with proper guidance, small-scale LLMs can exhibit exceptional performance in commonsense reasoning.

Large language model (LLM) companies provide Embedding as a Service (EaaS) to assist the individual in efficiently dealing with downstream tasks such as text classification and recommendation. However, recent works reveal the risk of the model stealing attack, posing a financial threat to EaaS providers. To protect the copyright of EaaS, we propose GuardEmb, a dynamic embedding watermarking method, striking a balance between enhancing watermark detectability and preserving embedding functionality. Our approach involves selecting special tokens and perturbing embeddings containing these tokens to inject watermarks. Simultaneously, we train a verifier to detect these watermarks. In the event of an attacker attempting to replicate our EaaS for profit, their model inherits our watermarks. For watermark verification, we construct verification texts to query the suspicious EaaS, and the verifier identifies our watermarks within the responses, effectively tracing copyright infringement. Extensive experiments across diverse datasets showcase the high detectability of our watermark method, even in out-of-distribution scenarios, without compromising embedding functionality. Our code is publicly available at https://github.com/Melodramass/Dynamic-Watermark.

Generative AI systems powered by Large Language Models have become increasingly popular in recent years. Lately, due to the risk of providing users with unsafe information, the adoption of those systems in safety-critical domains has raised significant concerns. To respond to this situation, input-output filters, commonly called guardrail models, have been proposed to complement other measures, such as model alignment. Unfortunately, the lack of a standard benchmark for guardrail models poses significant evaluation issues and makes it hard to compare results across scientific publications. To fill this gap, we introduce GuardBench, a large-scale benchmark for guardrail models comprising 40 safety evaluation datasets. To facilitate the adoption of GuardBench, we release a Python library providing an automated evaluation pipeline built on top of it. With our benchmark, we also share the first large-scale prompt moderation datasets in German, French, Italian, and Spanish. To assess the current state-of-the-art, we conduct an extensive comparison of recent guardrail models and show that a general-purpose instruction-following model of comparable size achieves competitive results without the need for specific fine-tuning.

How are we able to learn about complex current events just from short snippets of video? While natural language enables straightforward ways to represent under-specified, partially observable events, visual data does not facilitate analogous methods and, consequently, introduces unique challenges in event understanding. With the growing prevalence of vision-capable AI agents, these systems must be able to model events from collections of unstructured video data. To tackle robust event modeling in multimodal settings, we introduce a multimodal formulation for partially-defined events and cast the extraction of these events as a three-stage span retrieval task. We propose a corresponding benchmark for this task, MultiVENT-G, that consists of 14.5 hours of densely annotated current event videos and 1,168 text documents, containing 22.8K labeled event-centric entities. We propose a collection of LLM-driven approaches to the task of multimodal event analysis, and evaluate them on MultiVENT-G. Results illustrate the challenges that abstract event understanding poses and demonstrates promise in event-centric video-language systems.

We introduce a task and dataset for referring expression generation and comprehension in multi-agent embodied environments.In this task, two agents in a shared scene must take into account one another’s visual perspective, which may be different from their own, to both produce and understand references to objects in a scene and the spatial relations between them.We collect a dataset of 2,970 human-written referring expressions, each paired with human comprehension judgments, and evaluate the performance of automated models as speakers and listeners paired with human partners, finding that model performance in both reference generation and comprehension lags behind that of pairs of human agents.Finally, we experiment training an open-weight speaker model with evidence of communicative success when paired with a listener, resulting in an improvement from 58.9 to 69.3% in communicative success and even outperforming the strongest proprietary model.

Financial documents are filled with specialized terminology, arcane jargon, and curious acronyms that pose challenges for general-purpose text embeddings. Yet, few text embeddings specialized for finance have been reported in the literature, perhaps in part due to a lack of public datasets and benchmarks. We present BAM embeddings, a set of text embeddings finetuned on a carefully constructed dataset of 14.3M query-passage pairs including both public and proprietary financial documents. Demonstrating the benefits of domain-specific training, BAM embeddings achieve Recall@1 of 62.8% on a held-out test set, vs. only 39.2% for the best general-purpose text embedding from OpenAI. Further, BAM embeddings increase question answering accuracy by 8% on FinanceBench and show increased sensitivity to the finance-specific elements that are found in detailed, forward-looking and company and date-specific queries. To support further research we describe our approach in detail, quantify the importance of hard negative mining and dataset scale, and publicly release our embeddings.

Relation extraction (RE) aims to identify semantic relationships between entities within text. Despite considerable advancements, existing models predominantly require extensive annotated training data, which is both costly and labor-intensive to collect. Moreover, these models often struggle to adapt to new or unseen relations. Few-shot learning, aiming to lessen annotation demands, typically provides incomplete and biased supervision for target relations, leading to degraded and unstable performance. To accurately and explicitly describe relation semantics while minimizing annotation demands, we explore the definition only zero-shot RE setting where only relation definitions expressed in natural language are used to train a RE model. We introduce REPaL, comprising three stages: (1) We leverage large language models (LLMs) to generate initial seed instances from relation definitions and an unlabeled corpus. (2) We fine-tune a bidirectional Small Language Model (SLM) with initial seeds to learn relations for the target domain. (3) We expand pattern coverage and mitigate bias from initial seeds by integrating feedback from the SLM’s predictions on the unlabeled corpus and the synthesis history. To accomplish this, we leverage the multi-turn conversation ability of LLMs to generate new instances in follow-up dialogues, informed by both the feedback and synthesis history. Studies reveal that definition-oriented seed synthesis enhances pattern coverage whereas indiscriminately increasing seed quantity leads to performance saturation. Experiments on two datasets show REPaL significantly improved cost-effective zero-shot performance by large margins.

Long-context capabilities are essential for large language models (LLMs) to tackle complex and long-input tasks. Despite numerous efforts made to optimize LLMs for long contexts, challenges persist in robustly processing long inputs. In this paper, we introduce GraphReader, a graph-based agent system designed to handle long texts by structuring them into a graph and employing an agent to explore this graph autonomously. Upon receiving a question, the agent first undertakes a step-by-step analysis and devises a rational plan. It then invokes a set of predefined functions to read node content and neighbors, facilitating a coarse-to-fine exploration of the graph. Throughout the exploration, the agent continuously records new insights and reflects on current circumstances to optimize the process until it has gathered sufficient information to generate an answer. Experimental results on the LV-Eval dataset reveal that GraphReader using a 4k context window, consistently outperforms GPT-4-128k across context lengths from 16k to 256k by a large margin. Additionally, our approach demonstrates superior performance on four challenging single-hop and multi-hop benchmarks.

GraphQL is a powerful query language for APIs that allows clients to fetch precise data efficiently and flexibly, querying multiple resources with a single request. However, crafting complex GraphQL query operations can be challenging. Large Language Models (LLMs) offer an alternative by generating GraphQL queries from natural language, but they struggle due to limited exposure to publicly available GraphQL schemas, often resulting in invalid or suboptimal queries. Furthermore, no benchmark test data suite is available to reliably evaluate the performance of contemporary LLMs.To address this, we present a large-scale, cross-domain Text-to-GraphQL query operation dataset. The dataset includes 10,940 training triples spanning 185 cross-source data stores and 957 test triples over 14 data stores. Each triple consists of a GraphQL schema, GraphQL query operation, and corresponding natural language query. The dataset has been predominantly manually created, with natural language paraphrasing, and carefully validated, requiring approximately 1200 person-hours. In our evaluation, we tested 10 state-of-the-art LLMs using our test dataset. The best-performing model achieved an accuracy of only around 50% with one in-context few-shot example, underscoring the necessity for custom fine-tuning. To support further research and benchmarking, we are releasing the training and test datasets under the MIT License. The dataset is available at https://github.com/stepzen-dev/NL2GQL.

Long document classification presents challenges in capturing both local and global dependencies due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequately model hierarchical relationships within documents. To address these constraints, we propose a novel model leveraging a graph-tree structure. Our approach integrates syntax trees for sentence encodings and document graphs for document encodings, which capture fine-grained syntactic relationships and broader document contexts, respectively. We use Tree Transformers to generate sentence encodings, while a graph attention network models inter- and intra-sentence dependencies. During training, we implement bidirectional information propagation from word-to-sentence-to-document and vice versa, which enriches the contextual representation. Our proposed method enables a comprehensive understanding of content at all hierarchical levels and effectively handles arbitrarily long contexts without token limit constraints. Experimental results demonstrate the effectiveness of our approach in all types of long document classification tasks.

Applying differential privacy (DP) by means of the DP-SGD algorithm to protect individual data points during training is becoming increasingly popular in NLP. However, the choice of granularity at which DP is applied is often neglected. For example, neural machine translation (NMT) typically operates on the sentence-level granularity. From the perspective of DP, this setup assumes that each sentence belongs to a single person and any two sentences in the training dataset are independent. This assumption is however violated in many real-world NMT datasets, e.g., those including dialogues. For proper application of DP we thus must shift from sentences to entire documents. In this paper, we investigate NMT at both the sentence and document levels, analyzing the privacy/utility trade-off for both scenarios, and evaluating the risks of not using the appropriate privacy granularity in terms of leaking personally identifiable information (PII). Our findings indicate that the document-level NMT system is more resistant to membership inference attacks, emphasizing the significance of using the appropriate granularity when working with DP.

Vision Language Models (VLMs) are rapidly advancing in their capability to answer information-seeking questions. As these models are widely deployed in consumer applications, they could lead to new privacy risks due to emergent abilities to identify people in photos, geolocate images, etc. As we demonstrate, somewhat surprisingly, current open-source and proprietary VLMs are very capable image geolocators, making widespread geolocation with VLMs an immediate privacy risk, rather than merely a theoretical future concern. As a first step to address this challenge, we develop a new benchmark, GPTGeoChat, to test the capability of VLMs to moderate geolocation dialogues with users. We collect a set of 1,000 image geolocation conversations between in-house annotators and GPT-4v, which are annotated with the granularity of location information revealed at each turn. Using this new dataset we evaluate the ability of various VLMs to moderate GPT-4v geolocation conversations by determining when too much location information has been revealed. We find that custom fine-tuned models perform on par with prompted API-based models when identifying leaked location information at the country or city level, however fine-tuning on supervised data appears to be needed to accurately moderate finer granularities, such as the name of a restaurant or building.

Multimodal Named Entity Recognition and Grounding (MNERG) aims to extract paired textual and visual entities from texts and images. It has been well explored through a two-step paradigm: initially identifying potential visual entities using object detection methods and then aligning the extracted textual entities with their corresponding visual entities. However, when it comes to fine-grained MNERG, the long-tailed distribution of textual entity categories and the performance of object detectors limit the effectiveness of traditional methods. Specifically, more detailed classification leads to many low-frequency categories, and existing object detection methods often fail to pinpoint subtle regions within images. To address these challenges, we propose the Granular Entity Mapper (GEM) framework. Firstly, we design a multi-granularity entity recognition module, followed by a reranking module based on the Multimodal Large Language Model (MLLM) to incorporate hierarchical information of entity categories, visual cues, and external textual resources collectively for accurate fine-grained textual entity recognition. Then, we utilize a pre-trained Large Visual Language Model (LVLM) as an implicit visual entity grounder that directly deduces relevant visual entity regions from the entire image without the need for bounding box training. Experimental results on the GMNER and FMNERG datasets demonstrate that our GEM framework achieves state-of-the-art results on the fine-grained content extraction task.

An emergent research trend explores the use of Large Language Models (LLMs) as the backbone of agentic systems (e.g., SWE-Bench, Agent-Bench). To fulfill LLMs’ potential as autonomous agents, they must be able to identify, call, and interact with a variety of external tools and application program interfaces (APIs). This capability of LLMs, commonly termed function calling, leads to a myriad of advantages such as access to current and domain-specific information in databases and the outsourcing of tasks that can be reliably performed by tools. In this work, we introduce Granite-20B-FunctionCalling, a model trained using a multi-task training approach on seven fundamental tasks encompassed in function calling. Our comprehensive evaluation on multiple out-of-domain datasets, which compares Granite-20B-FunctionCalling to more than 15 other best proprietary and open models, shows that Granite-20B-FunctionCalling has better generalizability on multiple tasks across seven different evaluation benchmarks. Moreover, Granite-20B-FunctionCalling shows the best performance among all open models and ranks among the top on the Berkeley Function Calling Leaderboard (BFCL).

Large Language Models (LLMs) trained on web-scale text corpora have been shown to capture world knowledge in their parameters. However, the mechanism by which language models store different types of knowledge is poorly understood. In this work, we examine two types of knowledge relating to temporally sensitive entities and demonstrate that each type is localized to different sets of parameters within the LLMs. We hypothesize that the lack of consideration of the locality of knowledge in existing continual learning methods contributes to both: the failed uptake of new information, and catastrophic forgetting of previously learned information. We observe that sequences containing references to updated and newly mentioned entities exhibit larger gradient norms in a subset of layers. We demonstrate that targeting parameter updates to these relevant layers can improve the performance of continually pretraining on language containing temporal drift.

Privacy issues arise prominently during the inappropriate transmission of information between entities. Existing research primarily studies privacy by exploring various privacy attacks, defenses, and evaluations within narrowly predefined patterns, while neglecting that privacy is not an isolated, context-free concept limited to traditionally sensitive data (e.g., social security numbers), but intertwined with intricate social contexts that complicate the identification and analysis of potential privacy violations. The advent of Large Language Models (LLMs) offers unprecedented opportunities for incorporating the nuanced scenarios outlined in privacy laws to tackle these complex privacy issues. However, the scarcity of open-source relevant case studies restricts the efficiency of LLMs in aligning with specific legal statutes. To address this challenge, we introduce a novel framework, GoldCoin, designed to efficiently ground LLMs in privacy laws for judicial assessing privacy violations. Our framework leverages the theory of contextual integrity as a bridge, creating numerous synthetic scenarios grounded in relevant privacy statutes (e.g., HIPAA), to assist LLMs in comprehending the complex contexts for identifying privacy risks in the real world. Extensive experimental results demonstrate that GoldCoin markedly enhances LLMs’ capabilities in recognizing privacy risks across real court cases, surpassing the baselines on different judicial tasks.

While Large Language Models (LLMs) demonstrate impressive generation abilities, they frequently struggle when it comes to specialized domains due to their limited domain-specific knowledge. Studies on domain-specific LLMs resort to expanding the vocabulary before fine-tuning on domain-specific corpus, aiming to decrease the sequence length and enhance efficiency during decoding, without thoroughly investigating the results of vocabulary expansion to LLMs over different domains. Our pilot study reveals that expansion with only a subset of the entire vocabulary may lead to superior performance. Guided by the discovery, this paper explores how to identify a vocabulary subset to achieve the optimal results. We introduce VEGAD, an adaptive method that automatically identifies valuable words from a given domain vocabulary. Our method has been validated through experiments on three Chinese datasets, demonstrating its effectiveness. Additionally, we have undertaken comprehensive analyses of the method. The selection of a optimal subset for expansion has shown to enhance performance on both domain-specific tasks and general tasks, showcasing the potential of VEGAD.

Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) by integrating external knowledge bases, improving their performance in applications like fact-checking and information searching. In this paper, we demonstrate a security threat where adversaries can exploit the openness of these knowledge bases by injecting deceptive content into the retrieval database, intentionally changing the model’s behavior. This threat is critical as it mirrors real-world usage scenarios where RAG systems interact with publicly accessible knowledge bases, such as web scrapings and user-contributed data pools. To be more realistic, we target a realistic setting where the adversary has no knowledge of users’ queries, knowledge base data, and the LLM parameters. We demonstrate that it is possible to exploit the model successfully through crafted content uploads with access to the retriever. Our findings emphasize an urgent need for security measures in the design and deployment of RAG systems to prevent potential manipulation and ensure the integrity of machine-generated content.