Lihu Chen

Lihu Chen, Gaël Varoquaux

Large Language Models (LLMs) have made significant progress in advancing artificial general intelligence (AGI), leading to the development of increasingly large models such as GPT-4 and LLaMA-405B. However, scaling up model sizes results in exponentially higher computational costs and energy consumption, making these models impractical for academic researchers and businesses with limited resources. At the same time, Small Models (SMs) are frequently used in practical settings, although their significance is currently underestimated. This raises important questions about the role of small models in the era of LLMs, a topic that has received limited attention in prior research. In this work, we systematically examine the relationship between LLMs and SMs from two key perspectives: Collaboration and Competition. We hope this survey provides valuable insights for practitioners, fostering a deeper understanding of the contribution of small models and promoting more efficient use of computational resources. The code is available at https://github.com/tigerchen52/role_of_small_models

Lihu Chen, Gaël Varoquaux, Fabian M. Suchanek

Positional Encodings (PEs) are used to inject word-order information into transformer-based language models. While they can significantly enhance the quality of sentence representations, their specific contribution to language models is not fully understood, especially given recent findings that various positional encodings are insensitive to word order. In this work, we conduct a systematic study of positional encodings in \textbf{Bidirectional Masked Language Models} (BERT-style) , which complements existing work in three aspects: (1) We uncover the core function of PEs by identifying two common properties, Locality and Symmetry; (2) We show that the two properties are closely correlated with the performances of downstream tasks; (3) We quantify the weakness of current PEs by introducing two new probing tasks, on which current PEs perform poorly. We believe that these results are the basis for developing better PEs for transformer-based language models. The code is available at \faGithub~ \url{https://github.com/tigerchen52/locality\_symmetry}

Lihu Chen, Simon Razniewski, Gerhard Weikum

Despite their impressive scale, knowledge bases (KBs), such as Wikidata, still contain significant gaps. Language models (LMs) have been proposed as a source for filling these gaps. However, prior works have focused on prominent entities with rich coverage by LMs, neglecting the crucial case of long-tail entities. In this paper, we present a novel method for LM-based-KB completion that is specifically geared for facts about long-tail entities. The method leverages two different LMs in two stages: for candidate retrieval and for candidate verification and disambiguation. To evaluate our method and various baselines, we introduce a novel dataset, called MALT, rooted in Wikidata. Our method outperforms all baselines in F1, with major gains especially in recall.

Lihu Chen, Gaël Varoquaux, Fabian M. Suchanek

State-of-the-art NLP systems represent inputs with word embeddings, but these are brittle when faced with Out-of-Vocabulary (OOV) words. To address this issue, we follow the principle of mimick-like models to generate vectors for unseen words, by learning the behavior of pre-trained embeddings using only the surface form of words. We present a simple contrastive learning framework, LOVE, which extends the word representation of an existing pre-trained language model (such as BERT), and makes it robust to OOV with few additional parameters. Extensive evaluations demonstrate that our lightweight model achieves similar or even better performances than prior competitors, both on original datasets and on corrupted variants. Moreover, it can be used in a plug-and-play fashion with FastText and BERT, where it significantly improves their robustness.

Fabian Suchanek, Mehwish Alam, Thomas Bonald et al.

Knowledge Bases (KBs) find applications in many knowledge-intensive tasks and, most notably, in information retrieval. Wikidata is one of the largest public general-purpose KBs. Yet, its collaborative nature has led to a convoluted schema and taxonomy. The YAGO 4 KB cleaned up the taxonomy by incorporating the ontology of Schema.org, resulting in a cleaner structure amenable to automated reasoning. However, it also cut away large parts of the Wikidata taxonomy, which is essential for information retrieval. In this paper, we extend YAGO 4 with a large part of the Wikidata taxonomy - while respecting logical constraints and the distinction between classes and instances. This yields YAGO 4.5, a new, logically consistent version of YAGO that adds a rich layer of informative classes. An intrinsic and an extrinsic evaluation show the value of the new resource.

Lihu Chen, Gaël Varoquaux, Fabian M. Suchanek

Acronym Disambiguation (AD) is crucial for natural language understanding on various sources, including biomedical reports, scientific papers, and search engine queries. However, existing acronym disambiguation benchmarks and tools are limited to specific domains, and the size of prior benchmarks is rather small. To accelerate the research on acronym disambiguation, we construct a new benchmark named GLADIS with three components: (1) a much larger acronym dictionary with 1.5M acronyms and 6.4M long forms; (2) a pre-training corpus with 160 million sentences; (3) three datasets that cover the general, scientific, and biomedical domains. We then pre-train a language model, \emph{AcroBERT}, on our constructed corpus for general acronym disambiguation, and show the challenges and values of our new benchmark.

Gabriel Freedman, Adam Dejl, Adam Gould et al.

Claim verification is an important problem in high-stakes settings, including health and finance. When information underpinning claims is incomplete or conflicting, uncertain answers may be more appropriate than binary true or false classifications. In all cases, faithful explanations of the considerations determining the final verdict are crucial. We introduce inference-time argumentation (ITA), a trainable neurosymbolic framework for ternary claim verification in which a formal argumentation semantics giving the strength of claims is used both (i) to guide LLM training as models learn to generate arguments and assign them base scores (representing intrinsic strengths) and (ii) to compute ternary (true/false/uncertain) predictions from generated, scored arguments. As a result, at training time, argument generation and scoring can be optimised according to the quality of the induced argumentative predictions. Moreover, at inference time, the final prediction is faithful, by construction, to the arguments and scores determining the verdict, rather than being justified by a potentially unfaithful post-hoc reasoning trace as in conventional reasoning models. We finally show that, on two datasets for ternary claim verification, ITA improves upon argumentative baselines and can perform competitively against non-argumentative direct-prediction baselines, while providing verdicts that are computed deterministically from explicit, inspectable argumentative structures.

Lihu Chen, Xiang Yin, Francesca Toni

Understanding the internal thinking process of Large Language Models (LLMs) and the cause of hallucinations remains a key challenge. To this end, we introduce latent debate, a novel framework for interpreting model predictions through the lens of implicit internal arguments. Unlike the current work of self-consistency and multi-agent debate, which relies on explicit debates among multiple answers or multiple models, latent debate captures the hidden supporting and attacking signals that arise within a single model during a single inference. We first present a model- and task-agnostic conceptual framework, and then instantiate it symbolically to approximate the thinking process of LLMs on True/False prediction tasks. Empirical studies demonstrate that latent debate is a faithful structured surrogate model that has highly consistent predictions with the original LLM. Beyond interpretability, we demonstrate that latent debate provides a strong baseline for hallucination detection. Further analysis reveals strong correlations between hallucinations and debate patterns, such as a high degree of latent debates in the middle layers is linked to a higher risk of hallucinations. These findings position latent debate as a potential framework for understanding internal mechanisms of LLMs, especially for scenarios where internal (dis)agreements appear during the inference steps.

Lihu Chen, Shuojie Fu, Gabriel Freedman et al.

A significant and growing number of published scientific articles is found to involve fraudulent practices, posing a serious threat to the credibility and safety of research in fields such as medicine. We propose Pub-Guard-LLM, the first large language model-based system tailored to fraud detection of biomedical scientific articles. We provide three application modes for deploying Pub-Guard-LLM: vanilla reasoning, retrieval-augmented generation, and multi-agent debate. Each mode allows for textual explanations of predictions. To assess the performance of our system, we introduce an open-source benchmark, PubMed Retraction, comprising over 11K real-world biomedical articles, including metadata and retraction labels. We show that, across all modes, Pub-Guard-LLM consistently surpasses the performance of various baselines and provides more reliable explanations, namely explanations which are deemed more relevant and coherent than those generated by the baselines when evaluated by multiple assessment methods. By enhancing both detection performance and explainability in scientific fraud detection, Pub-Guard-LLM contributes to safeguarding research integrity with a novel, effective, open-source tool.

Lihu Chen, Gaël Varoquaux, Fabian M. Suchanek

Phrase representations play an important role in data science and natural language processing, benefiting various tasks like Entity Alignment, Record Linkage, Fuzzy Joins, and Paraphrase Classification. The current state-of-the-art method involves fine-tuning pre-trained language models for phrasal embeddings using contrastive learning. However, we have identified areas for improvement. First, these pre-trained models tend to be unnecessarily complex and require to be pre-trained on a corpus with context sentences. Second, leveraging the phrase type and morphology gives phrase representations that are both more precise and more flexible. We propose an improved framework to learn phrase representations in a context-free fashion. The framework employs phrase type classification as an auxiliary task and incorporates character-level information more effectively into the phrase representation. Furthermore, we design three granularities of data augmentation to increase the diversity of training samples. Our experiments across a wide range of tasks show that our approach generates superior phrase embeddings compared to previous methods while requiring a smaller model size. [PEARL-small]: https://huggingface.co/Lihuchen/pearl_small; [PEARL-base]: https://huggingface.co/Lihuchen/pearl_base; [Code and Dataset]: https://github.com/tigerchen52/PEARL

Lihu Chen, Alexandre Perez-Lebel, Fabian M. Suchanek et al.

Large Language Models (LLMs), including ChatGPT and LLaMA, are susceptible to generating hallucinated answers in a confident tone. While efforts to elicit and calibrate confidence scores have proven useful, recent findings show that controlling uncertainty must go beyond calibration: predicted scores may deviate significantly from the actual posterior probabilities due to the impact of grouping loss. In this work, we construct a new evaluation dataset derived from a knowledge base to assess confidence scores given to answers of Mistral and LLaMA. Experiments show that they tend to be overconfident. Further, we show that they are more overconfident on some answers than others, \emph{eg} depending on the nationality of the person in the query. In uncertainty-quantification theory, this is grouping loss. To address this, we propose a solution to reconfidence LLMs, canceling not only calibration but also grouping loss. The LLMs, after the reconfidencing process, indicate improved confidence alignment with the accuracy of their responses.

Lihu Chen, Gerard de Melo, Fabian M. Suchanek et al.

It is important for Large Language Models (LLMs) to be aware of the boundary of their knowledge, distinguishing queries they can confidently answer from those that lie beyond their capabilities. Such awareness enables models to perform adaptive inference, such as invoking retrieval-augmented generation (RAG), engaging in slow and deep thinking, or abstaining from answering when appropriate. These mechanisms are key to developing efficient and trustworthy AI. In this work, we propose a method to detect knowledge boundaries via Query-Level Uncertainty, which estimates if a model is capable of answering a given query before generating any tokens, thus avoiding the generation cost. To this end, we propose a novel, training-free method called Internal Confidence, which leverages self-evaluations across layers and tokens to provide a reliable signal of uncertainty. Empirical studies on both factual question answering and mathematical reasoning tasks demonstrate that our Internal Confidence outperforms several baselines in quality of confidence while being computationally cheaper. Furthermore, we demonstrate its benefits in adaptive inference settings, showing that for RAG and model cascading it reduces inference costs while preserving overall performance.

Kevin Zhou, Adam Dejl, Gabriel Freedman et al.

Research in uncertainty quantification (UQ) for large language models (LLMs) is increasingly important towards guaranteeing the reliability of this groundbreaking technology. We explore the integration of LLM UQ methods in argumentative LLMs (ArgLLMs), an explainable LLM framework for decision-making based on computational argumentation in which UQ plays a critical role. We conduct experiments to evaluate ArgLLMs' performance on claim verification tasks when using different LLM UQ methods, inherently performing an assessment of the UQ methods' effectiveness. Moreover, the experimental procedure itself is a novel way of evaluating the effectiveness of UQ methods, especially when intricate and potentially contentious statements are present. Our results demonstrate that, despite its simplicity, direct prompting is an effective UQ strategy in ArgLLMs, outperforming considerably more complex approaches.

Lisa Alazraki, Lihu Chen, Ana Brassard et al.

Large Language Models (LLMs) have achieved high accuracy on complex commonsense and mathematical problems that involve the composition of multiple reasoning steps. However, current compositional benchmarks testing these skills tend to focus on either commonsense or math reasoning, whereas LLM agents solving real-world tasks would require a combination of both. In this work, we introduce an Agentic Commonsense and Math benchmark (AgentCoMa), where each compositional task requires a commonsense reasoning step and a math reasoning step. We test it on 61 LLMs of different sizes, model families, and training strategies. We find that LLMs can usually solve both steps in isolation, yet their accuracy drops by ~30% on average when the two are combined. This is a substantially greater performance gap than the one we observe in prior compositional benchmarks that combine multiple steps of the same reasoning type. In contrast, non-expert human annotators can solve the compositional questions and the individual steps in AgentCoMa with similarly high accuracy. Furthermore, we conduct a series of interpretability studies to better understand the performance gap, examining neuron patterns, attention maps and membership inference. Our work underscores a substantial degree of model brittleness in the context of mixed-type compositional reasoning and offers a test bed for future improvement.

Lihu Chen, Adam Dejl, Francesca Toni

Large Language Models (LLMs) possess vast amounts of knowledge within their parameters, prompting research into methods for locating and editing this knowledge. Previous work has largely focused on locating entity-related (often single-token) facts in smaller models. However, several key questions remain unanswered: (1) How can we effectively locate query-relevant neurons in decoder-only LLMs, such as Llama and Mistral? (2) How can we address the challenge of long-form (or free-form) text generation? (3) Are there localized knowledge regions in LLMs? In this study, we introduce Query-Relevant Neuron Cluster Attribution (QRNCA), a novel architecture-agnostic framework capable of identifying query-relevant neurons in LLMs. QRNCA allows for the examination of long-form answers beyond triplet facts by employing the proxy task of multi-choice question answering. To evaluate the effectiveness of our detected neurons, we build two multi-choice QA datasets spanning diverse domains and languages. Empirical evaluations demonstrate that our method outperforms baseline methods significantly. Further, analysis of neuron distributions reveals the presence of visible localized regions, particularly within different domains. Finally, we show potential applications of our detected neurons in knowledge editing and neuron-based prediction.

Lihu Chen, Gaël Varoquaux, Fabian M. Suchanek

Biomedical entity linking aims to map biomedical mentions, such as diseases and drugs, to standard entities in a given knowledge base. The specific challenge in this context is that the same biomedical entity can have a wide range of names, including synonyms, morphological variations, and names with different word orderings. Recently, BERT-based methods have advanced the state-of-the-art by allowing for rich representations of word sequences. However, they often have hundreds of millions of parameters and require heavy computing resources, which limits their applications in resource-limited scenarios. Here, we propose a lightweight neural method for biomedical entity linking, which needs just a fraction of the parameters of a BERT model and much less computing resources. Our method uses a simple alignment layer with attention mechanisms to capture the variations between mention and entity names. Yet, we show that our model is competitive with previous work on standard evaluation benchmarks.