How Much are LLMs Contaminated? A Comprehensive Survey and the LLMSanitize Library

With the rise of Large Language Models (LLMs) in recent years, new opportunities are emerging, but also new challenges, and contamination is quickly becoming critical. Business applications and fundraising in AI have reached a scale at which a few percentage points gained on popular question-answering benchmarks could translate into dozens of millions of dollars, placing high pressure on model integrity. At the same time, it is becoming harder and harder to keep track of the data that LLMs have seen; if not impossible with closed-source models like GPT-4 and Claude-3 not divulging any information on the training set. As a result, contamination becomes a critical issue: LLMs' performance may not be reliable anymore, as the high performance may be at least partly due to their previous exposure to the data. This limitation jeopardizes the entire progress in the field of NLP, yet, there remains a lack of methods on how to efficiently address contamination, or a clear consensus on prevention, mitigation and classification of contamination. In this paper, we survey all recent work on contamination with LLMs, and help the community track contamination levels of LLMs by releasing an open-source Python library named LLMSanitize implementing major contamination detection algorithms, which link is: https://github.com/ntunlp/LLMSanitize.

ParaICL: Towards Robust Parallel In-Context Learning

Large language models (LLMs) have become the norm in natural language processing (NLP), excelling in few-shot in-context learning (ICL) with their remarkable abilities. Nonetheless, the success of ICL largely hinges on the choice of few-shot demonstration examples, making the selection process increasingly crucial. Existing methods have delved into optimizing the quantity and semantic similarity of these examples to improve ICL performances. However, our preliminary experiments indicate that the effectiveness of ICL is limited by the length of the input context. Moreover, varying combinations of few-shot demonstration examples can significantly boost accuracy across different test samples. To address this, we propose a novel method named parallel in-context learning (ParaICL) that effectively utilizes all demonstration examples without exceeding the manageable input context length. ParaICL employs parallel batching to distribute demonstration examples into different batches according to the semantic similarities of the questions in the demonstrations to the test question. It then computes normalized batch semantic scores for each batch. A weighted average semantic objective, constrained by adaptive plausibility, is applied to select the most appropriate tokens. Through extensive experiments, we validate the effectiveness of ParaICL and conduct ablation studies to underscore its design rationale. We further demonstrate that ParaICL can seamlessly integrate with existing methods.

ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?

Upon its release in late 2022, ChatGPT has brought a seismic shift in the entire landscape of AI, both in research and commerce. Through instruction-tuning a large language model (LLM) with supervised fine-tuning and reinforcement learning from human feedback, it showed that a model could answer human questions and follow instructions on a broad panel of tasks. Following this success, interests in LLMs have intensified, with new LLMs flourishing at frequent interval across academia and industry, including many start-ups focused on LLMs. While closed-source LLMs (e.g., OpenAI's GPT, Anthropic's Claude) generally outperform their open-source counterparts, the progress on the latter has been rapid with claims of achieving parity or even better on certain tasks. This has crucial implications not only on research but also on business. In this work, on the first anniversary of ChatGPT, we provide an exhaustive overview of this success, surveying all tasks where an open-source LLM has claimed to be on par or better than ChatGPT.

Is GPT-4 a Good Data Analyst?

As large language models (LLMs) have demonstrated their powerful capabilities in plenty of domains and tasks, including context understanding, code generation, language generation, data storytelling, etc., many data analysts may raise concerns if their jobs will be replaced by AI. This controversial topic has drawn a lot of attention in public. However, we are still at a stage of divergent opinions without any definitive conclusion. Motivated by this, we raise the research question of "is GPT-4 a good data analyst?" in this work and aim to answer it by conducting head-to-head comparative studies. In detail, we regard GPT-4 as a data analyst to perform end-to-end data analysis with databases from a wide range of domains. We propose a framework to tackle the problems by carefully designing the prompts for GPT-4 to conduct experiments. We also design several task-specific evaluation metrics to systematically compare the performance between several professional human data analysts and GPT-4. Experimental results show that GPT-4 can achieve comparable performance to humans. We also provide in-depth discussions about our results to shed light on further studies before we reach the conclusion that GPT-4 can replace data analysts.

Unlocking Temporal Question Answering for Large Language Models Using Code Execution

Large language models (LLMs) have made significant progress in natural language processing (NLP), and are utilized extensively in various applications. Recent works, such as chain-of-thought (CoT), have shown that intermediate reasoning steps can improve the performance of LLMs for complex reasoning tasks, such as math problems and symbolic question-answering tasks. However, we notice the challenge that LLMs face when it comes to temporal reasoning. Our preliminary experiments show that generating intermediate reasoning steps does not always boost the performance of complex temporal question-answering tasks. Therefore, we propose a novel framework that combines the extraction capability of LLMs and the logical reasoning capability of a Python solver to tackle this issue. Extensive experiments and analysis demonstrate the effectiveness of our framework in handling intricate time-bound reasoning tasks.

Chain of Knowledge: A Framework for Grounding Large Language Models with Structured Knowledge Bases

We introduce Chain of Knowledge (CoK), a framework that augments large language models with structured knowledge bases to improve factual correctness and reduce hallucination. Compared to previous works which only retrieve unstructured texts, CoK leverages structured knowledge bases which support complex queries and offer more direct factual statements. To assist large language models to effectively query knowledge bases, we propose a query generator model with contrastive instruction-tuning. As the query generator is separate from the frozen large language model, our framework is modular and thus easily adapted to various knowledge sources and models. Experiments show that our framework significantly enhances the factual correctness of large language models on knowledge-intensive tasks.

Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework

As large language models (LLMs) have become the norm in NLP, demonstrating good performance in generation and reasoning tasks, one of its most fatal disadvantages is the lack of factual correctness. Generating unfactual texts not only leads to lower performances but also degrades the trust and validity of their applications. Chain-of-Thought (CoT) prompting improves trust and model performance on complex reasoning tasks by generating interpretable reasoning chains, but still suffers from factuality concerns in knowledge-intensive tasks. In this paper, we propose the Verify-and-Edit framework for CoT prompting, which seeks to increase prediction factuality by post-editing reasoning chains according to external knowledge. Building on top of GPT-3, our framework lead to accuracy improvements in multiple open-domain question-answering tasks.

Retrieving Multimodal Information for Augmented Generation: A Survey

In this survey, we review methods that retrieve multimodal knowledge to assist and augment generative models. This group of works focuses on retrieving grounding contexts from external sources, including images, codes, tables, graphs, and audio. As multimodal learning and generative AI have become more and more impactful, such retrieval augmentation offers a promising solution to important concerns such as factuality, reasoning, interpretability, and robustness. We provide an in-depth review of retrieval-augmented generation in different modalities and discuss potential future directions. As this is an emerging field, we continue to add new papers and methods.

Is GPT-3 a Psychopath? Evaluating Large Language Models from a Psychological Perspective

Are large language models (LLMs) like GPT-3 psychologically safe? In this work, we design unbiased prompts to evaluate LLMs systematically from a psychological perspective. Firstly, we test the personality traits of three different LLMs with Short Dark Triad (SD-3) and Big Five Inventory (BFI). We find all of them show higher scores on SD-3 than the human average, indicating a relatively darker personality. Furthermore, LLMs like InstructGPT and FLAN-T5, which are fine-tuned with safety metrics, do not necessarily have more positive personalities. They score higher on Machiavellianism and Narcissism than GPT-3. Secondly, we test the LLMs in GPT-3 series on well-being tests to study the impact of fine-tuning with more training data. Interestingly, we observe a continuous increase in well-being scores from GPT-3 to InstructGPT. Following the observations, we show that instruction-finetune FLAN-T5 with positive answers in BFI can effectively improve the model from a psychological perspective. Finally, we call on the community to evaluate and improve LLMs' safety systematically instead of at the sentence level only.