EMNLP 2024 论文列表

This study explores enhancing grammatical error correction (GEC) through automatic error generation (AEG) using language models (LMs). Specifically, we fine-tune Llama 2 LMs for error generation and find that this approach yields synthetic errors akin to human errors. Next, we train GEC Llama models using these artificial errors and outperform previous state-of-the-art error correction models, with gains ranging between 0.8 and 6 F0.5 points across all tested languages (German, Ukrainian, and Estonian). Moreover, we demonstrate that generating errors by fine-tuning smaller sequence-to-sequence models and prompting large commercial LMs (GPT3.5 and GPT4) also results in synthetic errors beneficially affecting error generation models. We openly release trained models for error generation and correction as well as all the synthesized error datasets for the covered languages.

In addition to asking questions about facts in the world, some internet users—in particular, second language learners—ask questions about language itself. Depending on their proficiency level and audience, they may pose these questions in an L1 (first language) or an L2 (second language). We investigate how multilingual LLMs perform at crosslingual metalinguistic question answering. Focusing on binary questions about sentence grammaticality constructed from error-annotated learner corpora, we prompt three LLMs (Aya, Llama, and GPT) in multiple languages, including English, German, Korean, Russian, and Ukrainian. Our study reveals that the language of the prompt can significantly affect model performance, and despite English being the dominant training language for all three models, prompting in a different language with questions about English often yields better results.

The goal of text style transfer is to transform the style of texts while preserving their original meaning, often with only a few examples of the target style. Existing style transfer methods generally rely on the few-shot capabilities of large language models or on complex controllable text generation approaches that are inefficient and underperform on fluency metrics. We introduce TinyStyler, a lightweight but effective approach, which leverages a small language model (800M params) and pre-trained authorship embeddings to perform efficient, few-shot text style transfer. We evaluate on the challenging task of authorship style transfer and find TinyStyler outperforms strong approaches such as GPT-4. We also evaluate TinyStyler’s ability to perform text attribute style transfer (formal ↔ informal) with automatic and human evaluations and find that the approach outperforms recent controllable text generation methods.

Charts are important for presenting and explaining complex data relationships. Recently, multimodal large language models (MLLMs) have shown remarkable capabilities in chart understanding. However, the sheer size of these models limits their use in resource-constrained environments. In this paper, we present TinyChart, an efficient MLLM for chart understanding with only 3B parameters. TinyChart overcomes two key challenges in efficient chart understanding: (1) reduce the burden of learning numerical computations through Program-of-Thoughts (PoT) learning, which trains the model to generate Python programs for numerical calculations, and (2) reduce lengthy vision feature sequences through Vision Token Merging, which gradually merges most similar vision tokens. Extensive experiments demonstrate that our 3B TinyChart achieves SOTA performance on various chart understanding benchmarks including ChartQA, Chart-to-Text, Chart-to-Table, OpenCQA, and ChartX. It outperforms several chart-understanding MLLMs with up to 13B parameters, and close-sourced MLLM GPT-4V on ChartQA, with higher throughput during inference due to a smaller model scale and more efficient vision encoding.

Recent large language models (LLMs) have enabled the development of advanced agentic systems that can integrate various tools and APIs to fulfill user queries through function calling. However, the deployment of these LLMs on the edge has not been explored since they typically require cloud-based infrastructure due to their substantial model size and computational demands. To this end, we present TinyAgent, an end-to-end framework for training and deploying task-specific small language model agents capable of function calling for driving agentic systems at the edge. We first show how to enable accurate function calling for open-source models via the LLMCompiler framework. We then systematically curate a high-quality dataset for function calling, which we use to fine-tune two small language models, TinyAgent-1.1B and 7B. For efficient inference, we introduce a novel tool retrieval method to reduce the input prompt length and utilize quantization to further accelerate the inference speed. As a driving application, we demonstrate a local Siri-like system for Apple’s MacBook that can execute user commands through text or voice input. Our results show that our models can achieve, and even surpass, the function-calling capabilities of larger models like GPT-4-Turbo, while being fully deployed at the edge. We open-source our [dataset, models, and installable package](https://github.com/SqueezeAILab/TinyAgent) and provide a [demo video](https://www.youtube.com/watch?v=0GvaGL9IDpQ) for our MacBook assistant agent.

Temporal Knowledge Graph Question Answering (TKGQA) aims to answer temporal questions using knowledge in Temporal Knowledge Graphs (TKGs). Previous works employ pre-trained TKG embeddings or graph neural networks to incorporate the knowledge of TKGs. However, these methods fail to fully understand the complex semantic information of time constraints in questions.In contrast, Large Language Models (LLMs) have shown exceptional performance in knowledge graph reasoning, unifying both semantic understanding and structural reasoning. To further enhance LLMs’ temporal reasoning ability, this paper aims to integrate relevant temporal knowledge from TKGs into LLMs through a Time-aware Retrieve-Rewrite-Retrieve-Rerank framework, which we named TimeR4.Specifically, to reduce temporal hallucination in LLMs, we propose a retrieve-rewrite module to rewrite questions using background knowledge stored in the TKGs, thereby acquiring explicit time constraints. Then, we implement a retrieve-rerank module aimed at retrieving semantically and temporally relevant facts from the TKGs and reranking them according to the temporal constraints.To achieve this, we fine-tune a retriever using the contrastive time-aware learning framework.Our approach achieves great improvements, with relative gains of 47.8% and 22.5% on two datasets, underscoring its effectiveness in boosting the temporal reasoning abilities of LLMs. Our code is available at https://github.com/qianxinying/TimeR4.

Automated claim verification plays an essential role in fostering trust in the digital space. Despite the growing interest, the verification of temporal claims has not received much attention in the community. Temporal claim verification brings new challenges where cues of the temporal information need to be extracted, and temporal reasoning involving various temporal aspects of the text must be applied.In this work, we describe an end-to-end solution for temporal claim verification that considers the temporal information in claims to obtain relevant evidence sentences and harnesses the power of a large language model for temporal reasoning. We curate two datasets comprising a diverse range of temporal claims to learn time-sensitive representations that encapsulate not only the semantic relationships among the events, but also their chronological proximity.Experiment results demonstrate that the proposed approach significantly enhances the accuracy of temporal claim verification, thereby advancing current state-of-the-art in automated claim verification.

This paper revisits dynamic pruning through rank score thresholding in cluster-based sparse retrieval to skip the index partially at cluster and document levels during inference. It proposes a two-parameter pruning control scheme called ASC with a probabilistic guarantee on rank-safeness competitiveness. ASC uses cluster-level maximum weight segmentation to improve accuracy of rank score bound estimation and threshold-driven pruning, and is targeted for speeding up retrieval applications requiring high relevance competitiveness. The experiments with MS MARCO and BEIR show that ASC improves the accuracy and safeness of pruning for better relevance while delivering a low latency on a single-threaded CPU.

In conversational AI, large-scale models excel in various tasks but struggle with target-driven conversation planning. Current methods, such as chain-of-thought reasoning and tree-search policy learning techniques, either neglect plan rationality or require extensive human simulation procedures. Addressing this, we propose a novel two-stage framework, named EnPL, to improve the LLMs’ capability in planning conversations towards designated targets, including (1) distilling natural language plans from target-driven conversation corpus and (2) generating new plans with demonstration-guided in-context learning. Specifically, we first propose a filter approach to distill a high-quality plan dataset, ConvPlan (Resources of this paper can be found at https://github.com/pandazzh2020/ConvPlan). With the aid of corresponding conversational data and support from relevant knowledge bases, we validate the quality and rationality of these plans. Then, these plans are leveraged to help guide LLMs to further plan for new targets. Empirical results demonstrate that our method significantly improves the planning ability of LLMs, especially in target-driven conversations. Furthermore, EnPL is demonstrated to be quite effective in collecting target-driven conversation datasets and enhancing response generation, paving the way for constructing extensive target-driven conversational models.

The field of privacy-preserving Natural Language Processing has risen in popularity, particularly at a time when concerns about privacy grow with the proliferation of large language models. One solution consistently appearing in recent literature has been the integration of Differential Privacy (DP) into NLP techniques. In this paper, we take these approaches into critical view, discussing the restrictions that DP integration imposes, as well as bring to light the challenges that such restrictions entail. To accomplish this, we focus on **DP-Prompt**, a recent method for text privatization leveraging language models to rewrite texts. In particular, we explore this rewriting task in multiple scenarios, both with DP and without DP. To drive the discussion on the merits of DP in NLP, we conduct empirical utility and privacy experiments. Our results demonstrate the need for more discussion on the usability of DP in NLP and its benefits over non-DP approaches.

Self-detection for Large Language Models (LLMs) seeks to evaluate the trustworthiness of the LLM’s output by leveraging its own capabilities, thereby alleviating the issue of output hallucination. However, existing self-detection approaches only retrospectively evaluate answers generated by LLM, typically leading to the over-trust in incorrectly generated answers. To tackle this limitation, we propose a novel self-detection paradigm that considers the comprehensive answer space beyond LLM-generated answers. It thoroughly compares the trustworthiness of multiple candidate answers to mitigate the over-trust in LLM-generated incorrect answers. Building upon this paradigm, we introduce a two-step framework, which firstly instructs LLM to reflect and provide justifications for each candidate answer, and then aggregates the justifications for comprehensive target answer evaluation. This framework can be seamlessly integrated with existing approaches for superior self-detection. Extensive experiments on six datasets spanning three tasks demonstrate the effectiveness of the proposed framework.

Proving mathematical theorems using computer-verifiable formal languages like Lean significantly impacts mathematical reasoning. One approach to formal theorem proving involves generating complete proofs using Large Language Models (LLMs) based on Natural Language (NL) proofs. However, due to the scarcity of aligned NL and Formal Language (FL) theorem-proving data most modern LLMs exhibit suboptimal performance.This scarcity results in a paucity of methodologies for training LLMs and techniques to fully utilize their capabilities in composing formal proofs. To address these challenges, this paper proposes **TheoremLlama**, an end-to-end framework that trains a general-purpose LLM to be a Lean4 expert. **TheoremLlama** includes NL-FL dataset generation and bootstrapping method to obtain aligned dataset, curriculum learning and block training techniques to train the model, and iterative proof writing method to write Lean4 proofs that work together synergistically.Using the dataset generation method in **TheoremLlama**, we provide *Open Bootstrapped Theorems* (OBT), an NL-FL aligned and bootstrapped dataset. Our novel NL-FL bootstrapping method, where NL proofs are integrated into Lean4 code for training datasets, leverages the NL reasoning ability of LLMs for formal reasoning. The **TheoremLlama** framework achieves cumulative accuracies of 36.48% and 33.61% on MiniF2F-Valid and Test datasets respectively, surpassing the GPT-4 baseline of 22.95% and 25.41%. Our code, model checkpoints, and the generated dataset is published in GitHub

The evaluation of natural language generation (NLG) tasks is a significant and longstanding research area. With the recent emergence of powerful large language models (LLMs), some studies have turned to LLM-based automatic evaluation methods, which demonstrate great potential to become a new evaluation paradigm following traditional string-based and model-based metrics. However, despite the improved performance of existing methods, they still possess some deficiencies, such as dependency on references and limited evaluation flexibility. Therefore, in this paper, we meticulously construct a large-scale NLG evaluation corpus **NLG-Eval** with annotations from both human and GPT-4 to alleviate the lack of relevant data in this field. Furthermore, we propose **Themis**, an LLM dedicated to NLG evaluation, which has been trained with our designed multi-perspective consistency verification and rating-oriented preference alignment methods. Themis can conduct flexible and interpretable evaluations without references, and it exhibits superior evaluation performance on various NLG tasks, simultaneously generalizing well to unseen tasks and surpassing other evaluation models, including GPT-4.

Previous studies have examined the syntactic capabilities of large pre-trained language models, such as BERT, by using stimuli from psycholinguistic studies. Studying well-known processing errors, such as NPI illusive effects can reveal whether a model prioritizes linear or hierarchical information when processing language. Recent experiments have found that BERT is mildly susceptible to Negative Polarity Item (NPI) illusion effects (Shin et al., 2023; Vu and Lee, 2022). We expand on these results by examining the effect of distance on the illusive effect, using and modifying stimuli from Parker and Phillips (2016). We also further tease apart whether the model is more affected by hierarchical distance or linear distance. We find that BERT is highly sensitive to syntactic hierarchical information: added hierarchical layers affected its processing capabilities compared to added linear distance.

The disparity in the languages commonly studied in Natural Language Processing (NLP) is typically reflected by referring to languages as low vs high-resourced. However, there is limited consensus on what exactly qualifies as a ‘low-resource language.’ To understand how NLP papers define and study ‘low resource’ languages, we qualitatively analyzed 150 papers from the ACL Anthology and popular speech-processing conferences that mention the keyword ‘low-resource.’ Based on our analysis, we show how several interacting axes contribute to ‘low-resourcedness’ of a language and why that makes it difficult to track progress for each individual language. We hope our work (1) elicits explicit definitions of the terminology when it is used in papers and (2) provides grounding for the different axes to consider when connoting a language as low-resource.

The Chartered Financial Analyst (CFA) program is one of the most widely recognized financial certifications globally. In this work, we test a variety of state-of-the-art large language models (LLMs) on mock CFA exams to provide an overview of their financial analysis capabilities using the same evaluation standards applied for human professionals. We benchmark five leading proprietary models and eight open-source models on all three levels of the CFA through challenging multiple-choice and essay questions. We find that flagship proprietary models perform relatively well and can solidly pass levels I and II exams, but fail at level III due to essay questions. Open-source models generally fall short of estimated passing scores, but still show strong performance considering their size, cost, and availability advantages. We also find that using textbook data helps bridge the gap between open-source and proprietary models to a certain extent, despite reduced gains in CFA levels II and III. By understanding the current financial analysis abilities of LLMs, we aim to guide practitioners on which models are best suited for enhancing automation in the financial industry.

Word embeddings represent language vocabularies as clouds of d-dimensional points. We investigate how information is conveyed by the general shape of these clouds, instead of representing the semantic meaning of each token. Specifically, we use the notion of persistent homology from topological data analysis (TDA) to measure the distances between language pairs from the shape of their unlabeled embeddings. These distances quantify the degree of non-isometry of the embeddings. To distinguish whether these differences are random training errors or capture real information about the languages, we use the computed distance matrices to construct language phylogenetic trees over 81 Indo-European languages. Careful evaluation shows that our reconstructed trees exhibit strong and statistically-significant similarities to the reference.

Following multiple instructions is a crucial ability for large language models (LLMs). Evaluating this ability comes with significant challenges: (i) limited coherence between multiple instructions, (ii) positional bias where the order of instructions affects model performance, and (iii) a lack of objectively verifiable tasks. To address these issues, we introduce a benchmark designed to evaluate models’ abilities to follow multiple instructions through sequential instruction following (SIFo) tasks. In SIFo, the successful completion of multiple instructions is verifiable by examining only the final instruction. Our benchmark evaluates instruction following using four tasks (text modification, question answering, mathematics, and security rule following), each assessing different aspects of sequential instruction following. Our evaluation of popular LLMs, both closed-source and open-source, shows that more recent and larger models significantly outperform their older and smaller counterparts on the SIFo tasks, validating the benchmark’s effectiveness. All models struggle with following sequences of instructions, hinting at an important lack of robustness of today’s language models.

Recent development of large language models (LLMs) for code like CodeX and CodeT5+ shows promise in achieving code intelligence. Their ability of synthesizing program targeting a pre-defined algorithmic coding task has been intensively tested and verified on datasets including HumanEval and MBPP. Yet, evaluation of these LLMs from more perspectives (than just program synthesis) is also anticipated, considering their broad scope of applications. In this paper, we explore their ability of automatic test cases generation. We show intriguing observations and reveal how the quality of their generated test cases can be improved. Following recent work which uses generated test cases to enhance program synthesis, we further leverage our findings in improving the quality of the synthesized programs and show +11.77% and +4.22% higher code pass rates on HumanEval+ comparing with the GPT-3.5-turbo baseline and the recent state-of-the-art, respectively. Our code is publicly available at https://github.com/asdasxzxcq/TestCaseGen.