Large language models (LLMs) have demonstrated multilingual capabilities; yet, they are mostly English-centric due to the imbalanced training corpora. Existing works leverage this phenomenon to improve their multilingual performances through translation, primarily on natural language processing (NLP) tasks. This work extends the evaluation from NLP tasks to real user queries and from English-centric LLMs to non-English-centric LLMs. While translation into English can help improve the performance of multilingual NLP tasks for English-centric LLMs, it may not be optimal for all scenarios. For culture-related tasks that need deep language understanding, prompting in the native language tends to be more promising as it better captures the nuances of culture and language. Our experiments reveal varied behaviors among different LLMs and tasks in the multilingual context. Therefore, we advocate for more comprehensive multilingual evaluation and more efforts toward developing multilingual LLMs beyond English-centric ones.
相關內容
Large Language Models (LLMs) have demonstrated unprecedented prowess across various natural language processing tasks in various application domains. Recent studies show that LLMs can be leveraged to perform lexical semantic tasks, such as Knowledge Base Completion (KBC) or Ontology Learning (OL). However, it has not effectively been verified whether their success is due to their ability to reason over unstructured or semi-structured data, or their effective learning of linguistic patterns and senses alone. This unresolved question is particularly crucial when dealing with domain-specific data, where the lexical senses and their meaning can completely differ from what a LLM has learned during its training stage. This paper investigates the following question: Do LLMs really adapt to domains and remain consistent in the extraction of structured knowledge, or do they only learn lexical senses instead of reasoning? To answer this question and, we devise a controlled experiment setup that uses WordNet to synthesize parallel corpora, with English and gibberish terms. We examine the differences in the outputs of LLMs for each corpus in two OL tasks: relation extraction and taxonomy discovery. Empirical results show that, while adapting to the gibberish corpora, off-the-shelf LLMs do not consistently reason over semantic relationships between concepts, and instead leverage senses and their frame. However, fine-tuning improves the performance of LLMs on lexical semantic tasks even when the domain-specific terms are arbitrary and unseen during pre-training, hinting at the applicability of pre-trained LLMs for OL.
The advent of large language models (LLMs) has significantly advanced the field of code translation, enabling automated translation between programming languages. However, these models often struggle with complex translation tasks due to inadequate contextual understanding. This paper introduces a novel approach that enhances code translation through Few-Shot Learning, augmented with retrieval-based techniques. By leveraging a repository of existing code translations, we dynamically retrieve the most relevant examples to guide the model in translating new code segments. Our method, based on Retrieval-Augmented Generation (RAG), substantially improves translation quality by providing contextual examples from which the model can learn in real-time. We selected RAG over traditional fine-tuning methods due to its ability to utilize existing codebases or a locally stored corpus of code, which allows for dynamic adaptation to diverse translation tasks without extensive retraining. Extensive experiments on diverse datasets with open LLM models such as Starcoder, Llama3-70B Instruct, CodeLlama-34B Instruct, Granite-34B Code Instruct, and Mixtral-8x22B, as well as commercial LLM models like GPT-3.5 Turbo and GPT-4o, demonstrate our approach's superiority over traditional zero-shot methods, especially in translating between Fortran and CPP. We also explored varying numbers of shots i.e. examples provided during inference, specifically 1, 2, and 3 shots and different embedding models for RAG, including Nomic-Embed, Starencoder, and CodeBERT, to assess the robustness and effectiveness of our approach.
Common methods for aligning large language models (LLMs) with desired behaviour heavily rely on human-labelled data. However, as models grow increasingly sophisticated, they will surpass human expertise, and the role of human evaluation will evolve into non-experts overseeing experts. In anticipation of this, we ask: can weaker models assess the correctness of stronger models? We investigate this question in an analogous setting, where stronger models (experts) possess the necessary information to answer questions and weaker models (non-experts) lack this information. The method we evaluate is debate, where two LLM experts each argue for a different answer, and a non-expert selects the answer. We find that debate consistently helps both non-expert models and humans answer questions, achieving 76% and 88% accuracy respectively (naive baselines obtain 48% and 60%). Furthermore, optimising expert debaters for persuasiveness in an unsupervised manner improves non-expert ability to identify the truth in debates. Our results provide encouraging empirical evidence for the viability of aligning models with debate in the absence of ground truth.
Large language models (LLMs) and their fine-tuning techniques have demonstrated superior performance in various language understanding and generation tasks. This paper explores fine-tuning LLMs for stock return forecasting with financial newsflow. In quantitative investing, return forecasting is fundamental for subsequent tasks like stock picking, portfolio optimization, etc. We formulate the model to include text representation and forecasting modules. We propose to compare the encoder-only and decoder-only LLMs, considering they generate text representations in distinct ways. The impact of these different representations on forecasting performance remains an open question. Meanwhile, we compare two simple methods of integrating LLMs' token-level representations into the forecasting module. The experiments on real news and investment universes reveal that: (1) aggregated representations from LLMs' token-level embeddings generally produce return predictions that enhance the performance of long-only and long-short portfolios; (2) in the relatively large investment universe, the decoder LLMs-based prediction model leads to stronger portfolios, whereas in the small universes, there are no consistent winners. Among the three LLMs studied (DeBERTa, Mistral, Llama), Mistral performs more robustly across different universes; (3) return predictions derived from LLMs' text representations are a strong signal for portfolio construction, outperforming conventional sentiment scores.
Large language models (LLMs) have demonstrated impressive versatility across numerous tasks, yet their generalization capabilities remain poorly understood. To investigate these behaviors, arithmetic tasks serve as important venues. In previous studies, seemingly unrelated mysteries still exist -- (1) models with appropriate positional embeddings can correctly perform longer unseen arithmetic operations such as addition, but their effectiveness varies in more complex tasks like multiplication; (2) models perform well for longer unseen cases in modular addition under specific moduli (e.g., modulo 100) but struggle under very close moduli (e.g., modulo 101), regardless of the positional encoding used. We believe previous studies have been treating the symptoms rather than addressing the root cause -- they have paid excessive attention to improving model components, while overlooking the differences in task properties that may be the real drivers. This is confirmed by our unified theoretical framework for different arithmetic scenarios. For example, unlike multiplication, the digital addition task has the property of translation invariance which naturally aligns with the relative positional encoding, and this combination leads to successful generalization of addition to unseen longer domains. The discrepancy in operations modulo 100 and 101 arises from the base. Modulo 100, unlike 101, is compatible with the decimal system (base 10), such that unseen information in digits beyond the units digit and the tens digit is actually not needed for the task. Extensive experiments with GPT-like models validate our theoretical predictions. These findings deepen our understanding of the generalization mechanisms, and facilitate more data-efficient model training and objective-oriented AI alignment.
With the introduction of large language models (LLMs), automatic math reasoning has seen tremendous success. However, current methods primarily focus on providing solutions or using techniques like Chain-of-Thought to enhance problem-solving accuracy. In this paper, we focus on improving the capability of mathematics teaching via a Socratic teaching-based LLM (\texttt{SocraticLLM}), which guides learners toward profound thinking with clarity and self-discovery via conversation. We collect and release a high-quality mathematical teaching dataset, named \texttt{SocraticMATH}, which provides Socratic-style conversations of problems with extra knowledge. Also, we propose a knowledge-enhanced LLM as a strong baseline to generate reliable responses with review, guidance/heuristic, rectification, and summarization. Experimental results show the great advantages of \texttt{SocraticLLM} by comparing it with several strong generative models. The codes and datasets are available on \url{//github.com/ECNU-ICALK/SocraticMath}.
Large language models (LLMs) have shown remarkable performance on many different Natural Language Processing (NLP) tasks. Prompt engineering plays a key role in adding more to the already existing abilities of LLMs to achieve significant performance gains on various NLP tasks. Prompt engineering requires composing natural language instructions called prompts to elicit knowledge from LLMs in a structured way. Unlike previous state-of-the-art (SoTA) models, prompt engineering does not require extensive parameter re-training or fine-tuning based on the given NLP task and thus solely operates on the embedded knowledge of LLMs. Additionally, LLM enthusiasts can intelligently extract LLMs' knowledge through a basic natural language conversational exchange or prompt engineering, allowing more and more people even without deep mathematical machine learning background to experiment with LLMs. With prompt engineering gaining popularity in the last two years, researchers have come up with numerous engineering techniques around designing prompts to improve accuracy of information extraction from the LLMs. In this paper, we summarize different prompting techniques and club them together based on different NLP tasks that they have been used for. We further granularly highlight the performance of these prompting strategies on various datasets belonging to that NLP task, talk about the corresponding LLMs used, present a taxonomy diagram and discuss the possible SoTA for specific datasets. In total, we read and present a survey of 44 research papers which talk about 39 different prompting methods on 29 different NLP tasks of which most of them have been published in the last two years.
Recent advancements in large language models (LLMs) have catalyzed significant interest in the automatic generation of Register-Transfer Level (RTL) code, particularly Verilog, from natural language instructions. While commercial LLMs like ChatGPT have dominated this domain, open-source alternatives have lagged considerably in performance, limiting the flexibility and data privacy of this emerging technology. This study introduces a novel approach utilizing reinforcement learning with golden code feedback to enhance the performance of pre-trained models. Leveraging open-source data and base models, we have achieved state-of-the-art (SOTA) results with a substantial margin. Notably, our 6.7B parameter model \ours{} demonstrates superior performance compared to current best-in-class 13B and 16B models. Furthermore, through a comprehensive analysis of the limitations in direct fine-tuning and the training dynamics of reinforcement learning, we posit that the development of comprehensive supervisory signals, which are align with the inherent parallel semantics of Verilog code, is critical to effective generation. The code and data associated with this research are publicly available at \url{//github.com/CatIIIIIIII/veriseek}. The model weights can be accessed at \url{//huggingface.co/WANGNingroci/VeriSeek}.
Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars. However, in low-resource languages, obtaining such hand-picked exemplars can still be challenging, where unsupervised techniques may be necessary. Moreover, competent generative capabilities of LLMs are observed only in high-resource languages, while their performances among under-represented languages fall behind due to pre-training data imbalance. To elicit LLMs' ability onto low-resource languages without any supervised data, we propose to assemble synthetic exemplars from a diverse set of high-resource languages to prompt the LLMs to translate from any language into English. These prompts are then used to create intra-lingual exemplars to perform tasks in the target languages. Our unsupervised prompting method performs on par with supervised few-shot learning in LLMs of different sizes for translations between English and 13 Indic and 21 African low-resource languages. We also show that fine-tuning a 7B model on data generated from our method helps it perform competitively with a 175B model. In non-English translation tasks, our method even outperforms supervised prompting by up to 3 chrF++ in many low-resource languages. When evaluated on zero-shot multilingual summarization, our method surpasses other English-pivoting baselines by up to 4 ROUGE-L and is also favored by GPT-4.
Named entity recognition (NER) is the task to identify text spans that mention named entities, and to classify them into predefined categories such as person, location, organization etc. NER serves as the basis for a variety of natural language applications such as question answering, text summarization, and machine translation. Although early NER systems are successful in producing decent recognition accuracy, they often require much human effort in carefully designing rules or features. In recent years, deep learning, empowered by continuous real-valued vector representations and semantic composition through nonlinear processing, has been employed in NER systems, yielding stat-of-the-art performance. In this paper, we provide a comprehensive review on existing deep learning techniques for NER. We first introduce NER resources, including tagged NER corpora and off-the-shelf NER tools. Then, we systematically categorize existing works based on a taxonomy along three axes: distributed representations for input, context encoder, and tag decoder. Next, we survey the most representative methods for recent applied techniques of deep learning in new NER problem settings and applications. Finally, we present readers with the challenges faced by NER systems and outline future directions in this area.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191