Despite remarkable advancements in emulating human-like behavior through Large Language Models (LLMs), current textual simulations do not adequately address the notion of time. To this end, we introduce TimeArena, a novel textual simulated environment that incorporates complex temporal dynamics and constraints that better reflect real-life planning scenarios. In TimeArena, agents are asked to complete multiple tasks as soon as possible, allowing for parallel processing to save time. We implement the dependency between actions, the time duration for each action, and the occupancy of the agent and the objects in the environment. TimeArena grounds to 30 real-world tasks in cooking, household activity, and laboratory work. We conduct extensive experiments with various LLMs using TimeArena. Our findings reveal that even the most powerful models, e.g., GPT-4, still lag behind humans in effective multitasking, underscoring the need for enhanced temporal awareness in the development of language agents.
论文检索
输入标题、作者或关键词，从 1,915 篇学术成果中精准定位
The fine-tuning of Large Language Models (LLMs) specialized in code generation has seen notable advancements through the use of open-domain coding queries. Despite the successes, existing methodologies like Evol-Instruct encounter performance limitations, impeding further enhancements in code generation tasks. This paper examines the constraints of existing prompt evolution techniques and introduces a novel approach, Instruction Fusion (IF). IF innovatively combines two distinct prompts through a hybridization process, thereby enhancing the evolution of training prompts for code LLMs. Our experimental results reveal that the proposed novel method effectively addresses the shortcomings of prior methods, significantly improving the performance of Code LLMs across five code generation benchmarks, namely HumanEval, HumanEval+, MBPP, MBPP+ and MultiPL-E, which underscore the effectiveness of Instruction Fusion in advancing the capabilities of LLMs in code generation.
In this work, we introduce a semiparametric token-sequence co-supervision training method. It trains a language model by simultaneously leveraging supervision from the traditional next token prediction loss which is calculated over the parametric token embedding space and the next sequence prediction loss which is calculated over the nonparametric sequence embedding space. The nonparametric sequence embedding space is constructed by a separate language model tasked to condense an input text into a single representative embedding. Our experiments demonstrate that a model trained via both supervisions consistently surpasses models trained via each supervision independently. Analysis suggests that this co-supervision encourages a broader generalization capability across the model. Especially, the robustness of parametric token space which is established during the pretraining step tends to effectively enhance the stability of nonparametric sequence embedding space, a new space established by another language model.
Taxonomy completion, enriching existing taxonomies by inserting new concepts as parents or attaching them as children, has gained significant interest. Previous approaches embed concepts as vectors in Euclidean space, which makes it difficult to model asymmetric relations in taxonomy. In addition, they introduce pseudo-leaves to convert attachment cases into insertion cases, leading to an incorrect bias in network learning dominated by numerous pseudo-leaves. Addressing these, our framework, TaxBox, leverages box containment and center closeness to design two specialized geometric scorers within the box embedding space. These scorers are tailored for insertion and attachment operations and can effectively capture intrinsic relationships between concepts by optimizing on a granular box constraint loss. We employ a dynamic ranking loss mechanism to balance the scores from these scorers, allowing adaptive adjustments of insertion and attachment scores. Experiments on four real-world datasets show that TaxBox significantly outperforms previous methods, yielding substantial improvements over prior methods in real-world datasets, with average performance boosts of 6.7%, 34.9%, and 51.4% in MRR, Hit@1, and Prec@1, respectively.
OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
PDF ↗Recent advancements have seen Large Language Models (LLMs) and Large Multimodal Models (LMMs) surpassing general human capabilities in various tasks, approaching the proficiency level of human experts across multiple domains. With traditional benchmarks becoming less challenging for these models, new rigorous challenges are essential to gauge their advanced abilities. In this work, we present OlympiadBench, an Olympiad-level bilingual multimodal scientific benchmark, featuring 8,476 problems from Olympiad-level mathematics and physics competitions, including the Chinese college entrance exam. Each problem is detailed with expert-level annotations for step-by-step reasoning. Evaluating top-tier models on OlympiadBench, we implement a comprehensive assessment methodology to accurately evaluate model responses. Notably, the best-performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning. Our analysis orienting GPT-4V points out prevalent issues with hallucinations, knowledge omissions, and logical fallacies. We hope that our challenging benchmark can serve as a valuable resource for helping future AGI research endeavors. The data and evaluation code are available at https://github.com/OpenBMB/OlympiadBench
Event Causality Identification (ECI) aims to detect whether there exists a causal relation between two events in a document. Existing studies adopt a kind of *identifying after learning* paradigm, where events’ representations are first learned and then used for the identification. Furthermore, they mainly focus on the causality existence, but ignoring causal direction. In this paper, we take care of the causal direction and propose a new *identifying while learning* mode for the ECI task. We argue that a few causal relations can be easily identified with high confidence, and the directionality and structure of these identified causalities can be utilized to update events’ representations for boosting next round of causality identification. To this end, this paper designs an *iterative learning and identifying framework*: In each iteration, we construct an event causality graph, on which events’ causal structure representations are updated for boosting causal identification. Experiments on two public datasets show that our approach outperforms the state-of-the-art algorithms in both evaluations for causality existence identification and direction identification.
Understanding and Addressing the Under-Translation Problem from the Perspective of Decoding Objective
PDF ↗Neural Machine Translation (NMT) has made remarkable progress over the past years. However, under-translation and over-translation remain two challenging problems in state-of-the-art NMT systems. In this work, we conduct an in-depth analysis on the underlying cause of under-translation in NMT, providing an explanation from the perspective of decoding objective. To optimize the beam search objective, the model tends to overlook words it is less confident about, leading to the under-translation phenomenon. Correspondingly, the model’s confidence in predicting the End Of Sentence (EOS) diminishes when under-translation occurs, serving as a mild penalty for under-translated candidates. Building upon this analysis, we propose employing the confidence of predicting EOS as a detector for under-translation, and strengthening the confidence-based penalty to penalize candidates with a high risk of under-translation.Experiments on both synthetic and real-world data show that our method can accurately detect and rectify under-translated outputs, with minor impact on other correct translations.
Large language models (LLMs) have become a dominant and important tool for NLP researchers in a wide range of tasks. Today, many researchers use LLMs in synthetic data generation, task evaluation, fine-tuning, distillation, and other model-in-the-loop research workflows. However, challenges arise when using these models that stem from their scale, their closed source nature, and the lack of standardized tooling for these new and emerging workflows. The rapid rise to prominence of these models and these unique challenges has had immediate adverse impacts on open science and on the reproducibility of work that uses them. In this ACL 2024 theme track paper, we introduce DataDreamer, an open source Python library that allows researchers to write simple code to implement powerful LLM workflows. DataDreamer also helps researchers adhere to best practices that we propose to encourage open science and reproducibility. The library and documentation are available at: https://github.com/datadreamer-dev/DataDreamer.
MPCoder: Multi-user Personalized Code Generator with Explicit and Implicit Style Representation Learning
PDF ↗Large Language Models (LLMs) have demonstrated great potential for assisting developers in their daily development. However, most research focuses on generating correct code, how to use LLMs to generate personalized code has seldom been investigated. To bridge this gap, we proposed MPCoder (Multi-user Personalized Code Generator) to generate personalized code for multiple users. To better learn coding style features, we utilize explicit coding style residual learning to capture the syntax code style standards and implicit style learning to capture the semantic code style conventions. We train a multi-user style adapter to better differentiate the implicit feature representations of different users through contrastive learning, ultimately enabling personalized code generation for multiple users. We further propose a novel evaluation metric for estimating similarities between codes of different coding styles. The experimental results show the effectiveness of our approach for this novel task.
Mental manipulation, a significant form of abuse in interpersonal conversations, presents a challenge to identify due to its context-dependent and often subtle nature. The detection of manipulative language is essential for protecting potential victims, yet the field of Natural Language Processing (NLP) currently faces a scarcity of resources and research on this topic. Our study addresses this gap by introducing a new dataset, named \textsc{MentalManip}, which consists of 4,000 annotated fictional dialogues. This dataset enables a comprehensive analysis of mental manipulation, pinpointing both the techniques utilized for manipulation and the vulnerabilities targeted in victims. Our research further explores the effectiveness of leading-edge models in recognizing manipulative dialogue and its components through a series of experiments with various configurations. The results demonstrate that these models inadequately identify and categorize manipulative content. Attempts to improve their performance by fine-tuning with existing datasets on mental health and toxicity have not overcome these limitations. We anticipate that \textsc{MentalManip} will stimulate further research, leading to progress in both understanding and mitigating the impact of mental manipulation in conversations.
FLEUR: An Explainable Reference-Free Evaluation Metric for Image Captioning Using a Large Multimodal Model
PDF ↗Most existing image captioning evaluation metrics focus on assigning a single numerical score to a caption by comparing it with reference captions. However, these methods do not provide an explanation for the assigned score. Moreover, reference captions are expensive to acquire. In this paper, we propose FLEUR, an explainable reference-free metric to introduce explainability into image captioning evaluation metrics. By leveraging a large multimodal model, FLEUR can evaluate the caption against the image without the need for reference captions, and provide the explanation for the assigned score. We introduce score smoothing to align as closely as possible with human judgment and to be robust to user-defined grading criteria. FLEUR achieves high correlations with human judgment across various image captioning evaluation benchmarks and reaches state-of-the-art results on Flickr8k-CF, COMPOSITE, and Pascal-50S within the domain of reference-free evaluation metrics. Our source code and results are publicly available at: https://github.com/Yebin46/FLEUR.
Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inference
PDF ↗The customization of large language models (LLMs) for user-specified tasks gets important. However, maintaining all the customized LLMs on cloud servers incurs substantial memory and computational overheads, and uploading user data can also lead to privacy concerns. On-device LLMs can offer a promising solution by mitigating these issues. Yet, the performance of on-device LLMs is inherently constrained by the limitations of small-scaled models. To overcome these restrictions, we first propose Crayon, a novel approach for on-device LLM customization. Crayon begins by constructing a pool of diverse base adapters, and then we instantly blend them into a customized adapter without extra training. In addition, we develop a device-server hybrid inference strategy, which deftly allocates more demanding queries or non-customized tasks to a larger, more capable LLM on a server. This ensures optimal performance without sacrificing the benefits of on-device customization. We carefully craft a novel benchmark from multiple question-answer datasets, and show the efficacy of our method in the LLM customization.
ARL2: Aligning Retrievers with Black-box Large Language Models via Self-guided Adaptive Relevance Labeling
PDF ↗Retrieval-augmented generation enhances large language models (LLMs) by incorporating relevant information from external knowledge sources. This enables LLMs to adapt to specific domains and mitigate hallucinations in knowledge-intensive tasks. However, existing retrievers are often misaligned with LLMs due to separate training processes and the inherent black-box nature of LLMs. To address this challenge, we propose ARL2, a retriever learning technique that harnesses LLMs as labelers. ARL2 leverages LLMs to annotate and score adaptive relevance evidence, enabling the retriever to learn from robust LLM supervision. Furthermore, ARL2 incorporates a self-training strategy to minimize the cost of API calls. Extensive experiments demonstrate the effectiveness of ARL2, achieving accuracy improvements of 5.4% on NQ and 4.6% on MMLU compared to the state-of-the-art methods. Additionally, ARL2 exhibits robust transfer learning capabilities and strong zero-shot generalization abilities.
StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection
PDF ↗Streaming speech-to-text translation (StreamST) is the task of automatically translating speech while incrementally receiving an audio stream. Unlike simultaneous ST (SimulST), which deals with pre-segmented speech, StreamST faces the challenges of handling continuous and unbounded audio streams. This requires additional decisions about what to retain of the previous history, which is impractical to keep entirely due to latency and computational constraints. Despite the real-world demand for real-time ST, research on streaming translation remains limited, with existing works solely focusing on SimulST. To fill this gap, we introduce StreamAtt, the first StreamST policy, and propose StreamLAAL, the first StreamST latency metric designed to be comparable with existing metrics for SimulST. Extensive experiments across all 8 languages of MuST-C v1.0 show the effectiveness of StreamAtt compared to a naive streaming baseline and the related state-of-the-art SimulST policy, providing a first step in StreamST research.
Subtitling plays a crucial role in enhancing the accessibility of audiovisual content and encompasses three primary subtasks: translating spoken dialogue, segmenting translations into concise textual units, and estimating timestamps that govern their on-screen duration. Past attempts to automate this process rely, to varying degrees, on automatic transcripts, employed diversely for the three subtasks. In response to the acknowledged limitations associated with this reliance on transcripts, recent research has shifted towards transcription-free solutions for translation and segmentation, leaving the direct generation of timestamps as uncharted territory. To fill this gap, we introduce the first direct model capable of producing automatic subtitles, entirely eliminating any dependence on intermediate transcripts also for timestamp prediction. Experimental results, backed by manual evaluation, showcase our solution’s new state-of-the-art performance across multiple language pairs and diverse conditions.
When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP
PDF ↗Despite its crucial role in research experiments, code correctness is often presumed solely based on the perceived quality of results. This assumption, however, comes with the risk of erroneous outcomes and, in turn, potentially misleading findings. To mitigate this risk, we posit that the current focus on reproducibility should go hand in hand with the emphasis on software quality. We support our arguments with a case study in which we identify and fix three bugs in widely used implementations of the state-of-the-art Conformer architecture. Through experiments on speech recognition and translation in various languages, we demonstrate that the presence of bugs does not prevent the achievement of good and reproducible results, which however can lead to incorrect conclusions that potentially misguide future research. As countermeasures, we release pangoliNN, a library dedicated to testing neural models, and propose a Code-quality Checklist, with the goal of promoting coding best practices and improving software quality within the NLP community.
Although pre-training has become a prevalent approach for addressing various biomedical tasks, the current efficacy of pre-trained models is hindered by their reliance on a limited scope of medical sources. This limitation results in data scarcity during pre-training and restricts the range of applicable downstream tasks. In response to these challenges, we develop MedCSP, a new pre-training strategy designed to bridge the gap between multimodal medical sources. MedCSP employs modality-level aggregation to unify patient data within individual sources. Additionally, leveraging temporal information and diagnosis history, MedCSP effectively captures explicit and implicit correlations between patients across different sources. To evaluate the proposed strategy, we conduct comprehensive experiments, where the experiments are based on 6 modalities from 2 real-world medical data sources, and MedCSP is evaluated on 4 tasks against 19 baselines, marking an initial yet essential step towards cross-source modeling in the medical domain.
As natural language becomes the default interface for human-AI interaction, there is a need for LMs to appropriately communicate uncertainties in downstream applications. In this work, we investigate how LMs incorporate confidence in responses via natural language and how downstream users behave in response to LM-articulated uncertainties. We examine publicly deployed models and find that LMs are reluctant to express uncertainties when answering questions even when they produce incorrect responses. LMs can be explicitly prompted to express confidences, but tend to be overconfident, resulting in high error rates (an average of 47%) among confident responses. We test the risks of LM overconfidence by conducting human experiments and show that users rely heavily on LM generations, whether or not they are marked by certainty. Lastly, we investigate the preference-annotated datasets used in post training alignment and find that humans are biased against texts with uncertainty. Our work highlights new safety harms facing human-LM interactions and proposes design recommendations and mitigating strategies moving forward.
The reflection capacity of Large Language Model (LLM) has garnered extensive attention. A post-hoc prompting strategy, e.g., reflexion and self-refine, refines LLM’s response based on self-evaluated or external feedback. However, recent research indicates without external feedback, LLM’s intrinsic reflection is unstable. Our investigation unveils that the key bottleneck is the quality of the self-evaluated feedback. We find LLMs often exhibit overconfidence or high randomness when self-evaluate, offering stubborn or inconsistent feedback, which causes poor reflection. To remedy this, we advocate Self-Contrast: It adaptively explores diverse solving perspectives tailored to the request, contrasts the differences, and summarizes these discrepancies into a checklist which could be used to re-examine and eliminate discrepancies. Our method endows LLM with diverse perspectives to alleviate stubborn biases. Moreover, their discrepancies indicate potential errors or inherent uncertainties that LLM often overlooks. Reflecting upon these can catalyze more accurate and stable reflection. Experiments conducted on a series of reasoning and translation tasks with different LLMs serve to underscore the effectiveness and generality of our strategy.
What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection
PDF ↗Social media bot detection has always been an arms race between advancements in machine learning bot detectors and adversarial bot strategies to evade detection. In this work, we bring the arms race to the next level by investigating the opportunities and risks of state-of-the-art large language models (LLMs) in social bot detection. To investigate the opportunities, we design novel LLM-based bot detectors by proposing a mixture-of-heterogeneous-experts framework to divide and conquer diverse user information modalities. To illuminate the risks, we explore the possibility of LLM-guided manipulation of user textual and structured information to evade detection. Extensive experiments with three LLMs on two datasets demonstrate that instruction tuning on merely 1,000 annotated examples produces specialized LLMs that outperform state-of-the-art baselines by up to 9.1% on both datasets, while LLM-guided manipulation strategies could significantly bring down the performance of existing bot detectors by up to 29.6% and harm the calibration and reliability of bot detection systems.