The reliability of large language models (LLMs) is greatly compromised by their tendency to hallucinate, underscoring the need for precise identification of knowledge gaps within LLMs. Various methods for probing such gaps exist, ranging from calibration-based to prompting-based methods. To evaluate these probing methods, in this paper, we propose a new process based on using input variations and quantitative metrics. Through this, we expose two dimensions of inconsistency in knowledge gap probing. (1) Intra-method inconsistency: Minimal non-semantic perturbations in prompts lead to considerable variance in detected knowledge gaps within the same probing method; e.g., the simple variation of shuffling answer options can decrease agreement to around 40%. (2) Cross-method inconsistency: Probing methods contradict each other on whether a model knows the answer. Methods are highly inconsistent -- with decision consistency across methods being as low as 7% -- even though the model, dataset, and prompt are all the same. These findings challenge existing probing methods and highlight the urgent need for perturbation-robust probing frameworks.
Large Language Models (LLMs), despite achieving state-of-the-art results in a number of evaluation tasks, struggle to maintain their performance when logical reasoning is strictly required to correctly infer a prediction. In this work, we propose Argument Generation as a method of forcing models to utilize their reasoning capabilities when other approaches such as chain-of-thought reasoning prove insufficient. Our method involves the generation of arguments for each possible inference result, and asking the end model to rank the generated arguments. We show that Argument Generation can serve as an appropriate substitute for zero-shot prompting techniques without the requirement to add layers of complexity. Furthermore, we argue that knowledge-probing techniques such as chain-of-thought reasoning and Argument Generation are only useful when further reasoning is required to infer a prediction, making them auxiliary to more common zero-shot approaches. Finally, we demonstrate that our approach forces larger gains in smaller language models, showcasing a complex relationship between model size and prompting methods in foundation models.
Language model (LM) decoding is based on the next-token prediction (NTP) probability distribution. For neural LMs (e.g., Transformer-based), NTP distribution is essentially a softmax-regularized dot product between an encoded input context (query) and fixed vocabulary representations (keys). In this paper, we study the effect of the key distribution on the NTP distribution, with a focus on whether the similarity between keys will trigger spurious correlations in NTP. Through knowledge-probing tasks, we show that in the NTP distribution, the few top-ranked tokens are typically accurate. However, the middle-ranked prediction is highly biased towards the tokens that are distributionally (not necessarily semantically) similar to these top ones. For instance, if "P" is predicted as the top-1 token, "A"-"Z" will all be ranked high in NTP, no matter whether they can lead to correct decoding results. This hurts the sampling diversity and makes the sampling of correct, long-tail results hopeless and noisy. We attempt to alleviate this issue via a novel in-context method that iteratively pushes the query representation away from explored regions. Specifically, we include the explored decoding results in the context and prompt the LM to generate something else, which encourages the LM to produce a query representation that has small dot products with explored keys. Experiments on knowledge-probing tasks show that our method leads to efficient navigation away from explored keys to correct new keys. We further extend our method to open-ended and chain-of-thought (for reasoning) generation. Experiment results show that ICN contributes to better generation diversity and improved self-consistency voting performance. Finally, we discuss potential training issues caused by the fixed key space together with the challenges and possible ways to address them in future research.
Knowledge probing evaluates the extent to which a language model (LM) has acquired relational knowledge during its pre-training phase. It provides a cost-effective means of comparing LMs of different sizes and training setups and is useful for monitoring knowledge gained or lost during continual learning (CL). In prior work, we presented an improved knowledge probe called BEAR (Wiland et al., 2024), which enables the comparison of LMs trained with different pre-training objectives (causal and masked LMs) and addresses issues of skewed distributions in previous probes to deliver a more unbiased reading of LM knowledge. With this paper, we present LM-PUB- QUIZ, a Python framework and leaderboard built around the BEAR probing mechanism that enables researchers and practitioners to apply it in their work. It provides options for standalone evaluation and direct integration into the widely-used training pipeline of the Hugging Face TRANSFORMERS library. Further, it provides a fine-grained analysis of different knowledge types to assist users in better understanding the knowledge in each evaluated LM. We publicly release LM-PUB-QUIZ as an open-source project.
Graph learning methods have been extensively applied in diverse application areas. However, what kind of inherent graph properties e.g. graph proximity, graph structural information has been encoded into graph representation learning for downstream tasks is still under-explored. In this paper, we propose a novel graph probing framework (GraphProbe) to investigate and interpret whether the family of graph learning methods has encoded different levels of knowledge in graph representation learning. Based on the intrinsic properties of graphs, we design three probes to systematically investigate the graph representation learning process from different perspectives, respectively the node-wise level, the path-wise level, and the structural level. We construct a thorough evaluation benchmark with nine representative graph learning methods from random walk based approaches, basic graph neural networks and self-supervised graph methods, and probe them on six benchmark datasets for node classification, link prediction and graph classification. The experimental evaluation verify that GraphProbe can estimate the capability of graph representation learning. Remaking results have been concluded: GCN and WeightedGCN methods are relatively versatile methods achieving better results with respect to different tasks.
Language models often struggle with handling factual knowledge, exhibiting factual hallucination issue. This makes it vital to evaluate the models' ability to recall its parametric knowledge about facts. In this study, we introduce a knowledge probing benchmark, BELIEF(ICL), to evaluate the knowledge recall ability of both encoder- and decoder-based pre-trained language models (PLMs) from diverse perspectives. BELIEFs utilize a multi-prompt dataset to evaluate PLM's accuracy, consistency, and reliability in factual knowledge recall. To enable a more reliable evaluation with BELIEFs, we semi-automatically create MyriadLAMA, which has massively diverse prompts. We validate the effectiveness of BELIEFs in comprehensively evaluating PLM's knowledge recall ability on diverse PLMs, including recent large language models (LLMs). We then investigate key factors in memorizing and recalling facts in PLMs, such as model size, pretraining strategy and corpora, instruction-tuning process and in-context learning settings. Finally, we reveal the limitation of the prompt-based knowledge probing. The MyriadLAMA is publicized.
This study explores the sycophantic tendencies of Large Language Models (LLMs), where these models tend to provide answers that match what users want to hear, even if they are not entirely correct. The motivation behind this exploration stems from the common behavior observed in individuals searching the internet for facts with partial or misleading knowledge. Similar to using web search engines, users may recall fragments of misleading keywords and submit them to an LLM, hoping for a comprehensive response. Our empirical analysis of several LLMs shows the potential danger of these models amplifying misinformation when presented with misleading keywords. Additionally, we thoroughly assess four existing hallucination mitigation strategies to reduce LLMs sycophantic behavior. Our experiments demonstrate the effectiveness of these strategies for generating factually correct statements. Furthermore, our analyses delve into knowledge-probing experiments on factual keywords and different categories of sycophancy mitigation.
Knowledge probing assesses to which degree a language model (LM) has successfully learned relational knowledge during pre-training. Probing is an inexpensive way to compare LMs of different sizes and training configurations. However, previous approaches rely on the objective function used in pre-training LMs and are thus applicable only to masked or causal LMs. As a result, comparing different types of LMs becomes impossible. To address this, we propose an approach that uses an LM's inherent ability to estimate the log-likelihood of any given textual statement. We carefully design an evaluation dataset of 7,731 instances (40,916 in a larger variant) from which we produce alternative statements for each relational fact, one of which is correct. We then evaluate whether an LM correctly assigns the highest log-likelihood to the correct statement. Our experimental evaluation of 22 common LMs shows that our proposed framework, BEAR, can effectively probe for knowledge across different LM types. We release the BEAR datasets and an open-source framework that implements the probing approach to the research community to facilitate the evaluation and development of LMs.
Large Language Models (LLMs) demonstrate an impressive capacity to recall a vast range of factual knowledge. However, understanding their underlying reasoning and internal mechanisms in exploiting this knowledge remains a key research area. This work unveils the factual information an LLM represents internally for sentence-level claim verification. We propose an end-to-end framework to decode factual knowledge embedded in token representations from a vector space to a set of ground predicates, showing its layer-wise evolution using a dynamic knowledge graph. Our framework employs activation patching, a vector-level technique that alters a token representation during inference, to extract encoded knowledge. Accordingly, we neither rely on training nor external models. Using factual and common-sense claims from two claim verification datasets, we showcase interpretability analyses at local and global levels. The local analysis highlights entity centrality in LLM reasoning, from claim-related information and multi-hop reasoning to representation errors causing erroneous evaluation. On the other hand, the global reveals trends in the underlying evolution, such as word-based knowledge evolving into claim-related facts. By interpreting semantics from LLM latent representations and enabling graph-related analyses, this work enhances the understanding of the factual knowledge resolution process.
KEPLMs are pre-trained models that utilize external knowledge to enhance language understanding. Previous language models facilitated knowledge acquisition by incorporating knowledge-related pre-training tasks learned from relation triples in knowledge graphs. However, these models do not prioritize learning embeddings for entity-related tokens. Moreover, updating the entire set of parameters in KEPLMs is computationally demanding. This paper introduces TRELM, a Robust and Efficient Pre-training framework for Knowledge-Enhanced Language Models. We observe that entities in text corpora usually follow the long-tail distribution, where the representations of some entities are suboptimally optimized and hinder the pre-training process for KEPLMs. To tackle this, we employ a robust approach to inject knowledge triples and employ a knowledge-augmented memory bank to capture valuable information. Furthermore, updating a small subset of neurons in the feed-forward networks (FFNs) that store factual knowledge is both sufficient and efficient. Specifically, we utilize dynamic knowledge routing to identify knowledge paths in FFNs and selectively update parameters during pre-training. Experimental results show that TRELM reduces pre-training time by at least 50% and outperforms other KEPLMs in knowledge probing tasks and multiple knowledge-aware language understanding tasks.
Acquiring factual knowledge for language models (LMs) in low-resource languages poses a serious challenge, thus resorting to cross-lingual transfer in multilingual LMs (ML-LMs). In this study, we ask how ML-LMs acquire and represent factual knowledge. Using the multilingual factual knowledge probing dataset, mLAMA, we first conducted a neuron investigation of ML-LMs (specifically, multilingual BERT). We then traced the roots of facts back to the knowledge source (Wikipedia) to identify the ways in which ML-LMs acquire specific facts. We finally identified three patterns of acquiring and representing facts in ML-LMs: language-independent, cross-lingual shared and transferred, and devised methods for differentiating them. Our findings highlight the challenge of maintaining consistent factual knowledge across languages, underscoring the need for better fact representation learning in ML-LMs.
We evaluate the ability of Large Language Models (LLMs) to discern and express their internal knowledge state, a key factor in countering factual hallucination and ensuring reliable application of LLMs. We observe a robust self-awareness of internal knowledge state in LLMs, evidenced by over 85% accuracy in knowledge probing. However, LLMs often fail to express their internal knowledge during generation, leading to factual hallucinations. We develop an automated hallucination annotation tool, Dreamcatcher, which merges knowledge probing and consistency checking methods to rank factual preference data. Using knowledge preference as reward, We propose a Reinforcement Learning from Knowledge Feedback (RLKF) training framework, leveraging reinforcement learning to enhance the factuality and honesty of LLMs. Our experiments across multiple models show that RLKF training effectively enhances the ability of models to utilize their internal knowledge state, boosting performance in a variety of knowledge-based and honesty-related tasks.
Large language models (LLMs) are increasingly adopted for a variety of tasks with implicit graphical structures, such as planning in robotics, multi-hop question answering or knowledge probing, structured commonsense reasoning, and more. While LLMs have advanced the state-of-the-art on these tasks with structure implications, whether LLMs could explicitly process textual descriptions of graphs and structures, map them to grounded conceptual spaces, and perform structured operations remains underexplored. To this end, we propose NLGraph (Natural Language Graph), a comprehensive benchmark of graph-based problem solving designed in natural language. NLGraph contains 29,370 problems, covering eight graph reasoning tasks with varying complexity from simple tasks such as connectivity and shortest path up to complex problems such as maximum flow and simulating graph neural networks. We evaluate LLMs (GPT-3/4) with various prompting approaches on the NLGraph benchmark and find that 1) language models do demonstrate preliminary graph reasoning abilities, 2) the benefit of advanced prompting and in-context learning diminishes on more complex graph problems, while 3) LLMs are also (un)surprisingly brittle in the face of spurious correlations in graph and problem settings. We then propose Build-a-Graph Prompting and Algorithmic Prompting, two instruction-based approaches to enhance LLMs in solving natural language graph problems. Build-a-Graph and Algorithmic prompting improve the performance of LLMs on NLGraph by 3.07% to 16.85% across multiple tasks and settings, while how to solve the most complicated graph reasoning tasks in our setup with language models remains an open research question. The NLGraph benchmark and evaluation code are available at https://github.com/Arthur-Heng/NLGraph.
Multilingual pretrained language models serve as repositories of multilingual factual knowledge. Nevertheless, a substantial performance gap of factual knowledge probing exists between high-resource languages and low-resource languages, suggesting limited implicit factual knowledge transfer across languages in multilingual pretrained language models. This paper investigates the feasibility of explicitly transferring relatively rich factual knowledge from English to non-English languages. To accomplish this, we propose two parameter-free $\textbf{L}$anguage $\textbf{R}$epresentation $\textbf{P}$rojection modules (LRP2). The first module converts non-English representations into English-like equivalents, while the second module reverts English-like representations back into representations of the corresponding non-English language. Experimental results on the mLAMA dataset demonstrate that LRP2 significantly improves factual knowledge retrieval accuracy and facilitates knowledge transferability across diverse non-English languages. We further investigate the working mechanism of LRP2 from the perspectives of representation space and cross-lingual knowledge neuron.
Pre-trained Language Models (PLMs) are trained on vast unlabeled data, rich in world knowledge. This fact has sparked the interest of the community in quantifying the amount of factual knowledge present in PLMs, as this explains their performance on downstream tasks, and potentially justifies their use as knowledge bases. In this work, we survey methods and datasets that are used to probe PLMs for factual knowledge. Our contributions are: (1) We propose a categorization scheme for factual probing methods that is based on how their inputs, outputs and the probed PLMs are adapted; (2) We provide an overview of the datasets used for factual probing; (3) We synthesize insights about knowledge retention and prompt optimization in PLMs, analyze obstacles to adopting PLMs as knowledge bases and outline directions for future work.
Although the mapping between sound and meaning in human language is assumed to be largely arbitrary, research in cognitive science has shown that there are non-trivial correlations between particular sounds and meanings across languages and demographic groups, a phenomenon known as sound symbolism. Among the many dimensions of meaning, sound symbolism is particularly salient and well-demonstrated with regards to cross-modal associations between language and the visual domain. In this work, we address the question of whether sound symbolism is reflected in vision-and-language models such as CLIP and Stable Diffusion. Using zero-shot knowledge probing to investigate the inherent knowledge of these models, we find strong evidence that they do show this pattern, paralleling the well-known kiki-bouba effect in psycholinguistics. Our work provides a novel method for demonstrating sound symbolism and understanding its nature using computational tools. Our code will be made publicly available.
Biomedical language understanding benchmarks are the driving forces for artificial intelligence applications with large language model (LLM) back-ends. However, most current benchmarks: (a) are limited to English which makes it challenging to replicate many of the successes in English for other languages, or (b) focus on knowledge probing of LLMs and neglect to evaluate how LLMs apply these knowledge to perform on a wide range of bio-medical tasks, or (c) have become a publicly available corpus and are leaked to LLMs during pre-training. To facilitate the research in medical LLMs, we re-build the Chinese Biomedical Language Understanding Evaluation (CBLUE) benchmark into a large scale prompt-tuning benchmark, PromptCBLUE. Our benchmark is a suitable test-bed and an online platform for evaluating Chinese LLMs' multi-task capabilities on a wide range bio-medical tasks including medical entity recognition, medical text classification, medical natural language inference, medical dialogue understanding and medical content/dialogue generation. To establish evaluation on these tasks, we have experimented and report the results with the current 9 Chinese LLMs fine-tuned with differtent fine-tuning techniques.
Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. LLMs are typically evaluated using accuracy, yet this metric does not capture the vulnerability of LLMs to hallucination-inducing factors like prompt and context variability. How do we evaluate the capabilities of LLMs to consistently produce factually correct answers? In this paper, we propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability. MONITOR computes the distance between the probability distributions of a valid output and its counterparts produced by the same LLM probing the same fact using different styles of prompts and contexts.Experiments on a comprehensive range of 12 LLMs demonstrate the effectiveness of MONITOR in evaluating the factual reliability of LLMs while maintaining a low computational overhead. In addition, we release the FKTC (Factual Knowledge Test Corpus) test set, containing 210,158 prompts in total to foster research along this line (https://github.com/Vicky-Wil/MONITOR).
In this work, we explore the use of Large Language Models (LLMs) for knowledge engineering tasks in the context of the ISWC 2023 LM-KBC Challenge. For this task, given subject and relation pairs sourced from Wikidata, we utilize pre-trained LLMs to produce the relevant objects in string format and link them to their respective Wikidata QIDs. We developed a pipeline using LLMs for Knowledge Engineering (LLMKE), combining knowledge probing and Wikidata entity mapping. The method achieved a macro-averaged F1-score of 0.701 across the properties, with the scores varying from 1.00 to 0.328. These results demonstrate that the knowledge of LLMs varies significantly depending on the domain and that further experimentation is required to determine the circumstances under which LLMs can be used for automatic Knowledge Base (e.g., Wikidata) completion and correction. The investigation of the results also suggests the promising contribution of LLMs in collaborative knowledge engineering. LLMKE won Track 2 of the challenge. The implementation is available at https://github.com/bohuizhang/LLMKE.
Recent breakthroughs in pre-trained code models, such as CodeBERT and Codex, have shown their superior performance in various downstream tasks. The correctness and unambiguity of API usage among these code models are crucial for achieving desirable program functionalities, requiring them to learn various API fully qualified names structurally and semantically. Recent studies reveal that even state-of-the-art pre-trained code models struggle with suggesting the correct APIs during code generation. However, the reasons for such poor API usage performance are barely investigated. To address this challenge, we propose using knowledge probing as a means of interpreting code models, which uses cloze-style tests to measure the knowledge stored in models. Our comprehensive study examines a code model's capability of understanding API fully qualified names from two different perspectives: API call and API import. Specifically, we reveal that current code models struggle with understanding API names, with pre-training strategies significantly affecting the quality of API name learning. We demonstrate that natural language context can assist code models in locating Python API names and generalize Python API name knowledge to unseen data. Our findings provide insights into the limitations and capabilities of current pre-trained code models, and suggest that incorporating API structure into the pre-training process can improve automated API usage and code representations. This work provides significance for advancing code intelligence practices and direction for future studies. All experiment results, data and source code used in this work are available at \url{https://doi.org/10.5281/zenodo.7902072}.