Most existing retrieval-augmented language models (LMs) assume a naive dichotomy within a retrieved document set: query-relevance and irrelevance. Our work investigates a more challenging scenario in which even the “relevant” documents may contain misleading or incorrect information, causing conflict among the retrieved documents and thereby negatively influencing model decisions as noise. We observe that existing LMs are highly brittle to the presence of conflicting information in both the fine-tuning and in-context few-shot learning scenarios. We propose approaches for handling knowledge conflicts among retrieved documents by explicitly fine-tuning a discriminator or prompting GPT-3.5 to elicit its discriminative capability. Our empirical results on open-domain QA show that these approaches significantly enhance model robustness. We also provide our findings on incorporating the fine-tuned discriminator’s decision into the in-context learning process, proposing a way to exploit the benefits of two disparate learning schemes. Alongside our findings, we provide MacNoise, a machine-generated, conflict-induced dataset to further encourage research in this direction.

The NLI4CT task assesses Natural Language Inference systems in predicting whether hypotheses entail or contradict evidence from Clinical Trial Reports. In this study, we evaluate various Large Language Models (LLMs) with multiple strategies, including Chain-of-Thought, In-Context Learning, and Parameter-Efficient Fine-Tuning (PEFT). We propose a PEFT method to improve the consistency of LLMs by merging adapters that were fine-tuned separately using triplet and language modelling objectives. We found that merging the two PEFT adapters improves the F1 score (+0.0346) and consistency (+0.152) of the LLMs. However, our novel methods did not produce more accurate results than GPT-4 in terms of faithfulness and consistency. Averaging the three metrics, GPT-4 ranks joint-first in the competition with 0.8328. Finally, our contamination analysis with GPT-4 indicates that there was no test data leakage. Our code is available at https://github.com/EdinburghClinicalNLP/semeval_nli4ct.

Compositional reasoning across texts has been a long-standing challenge in natural language processing. With large language models like GPT-4 taking over the field, prompting techniques such as chain-of-thought (CoT) were proposed to unlock compositional, multi-step reasoning capabilities of LLMs. Despite their success, the prompts demand significant human effort to discover and validate them. Our work draws attention to the idea of transferring task-specific inductive biases from finetuned models to prompts, as a way of improving GPT-4’s compositional reasoning capabilities. To leverage these inductive biases, we formulate prompt templates to ease the transfer of inductive biases. The experimental results on multi-hop question answering and numerical reasoning over text show that our proposed prompt scheme shows competitive zero-shot and few-shot performances compared to existing prompts on complicated reasoning tasks, highlighting the importance of adopting the validated biases of the previous paradigm.

A graph is a suitable data structure to represent the structural information of text. Recently, multi-hop question answering (MHQA) tasks, which require inter-paragraph/sentence linkages, have come to exploit such properties of a graph. Previous approaches to MHQA relied on leveraging the graph information along with the pre-trained language model (PLM) encoders. However, this trend exhibits the following drawbacks: (i) sample inefficiency while training in a low-resource setting; (ii) lack of reusability due to changes in the model structure or input. Our work proposes the Graph-Induced Transformer (GIT) that applies graph-derived attention patterns directly into a PLM, without the need to employ external graph modules. GIT can leverage the useful inductive bias of graphs while retaining the unperturbed Transformer structure and parameters. Our experiments on HotpotQA successfully demonstrate both the sample efficient characteristic of GIT and its capacity to replace the graph modules while preserving model performance.

Numerical reasoning over text is a challenging subtask in question answering (QA) that requires both the understanding of texts and numbers. However, existing language models in these numerical reasoning QA models tend to overly rely on the pre-existing parametric knowledge at inference time, which commonly causes hallucination in interpreting numbers. Our work proposes a novel attention masked reasoning model, the NC-BERT, that learns to leverage the number-related contextual knowledge to alleviate the over-reliance on parametric knowledge and enhance the numerical reasoning capabilities of the QA model. The empirical results suggest that understanding of numbers in their context by reducing the parametric knowledge influence, and refining numerical information in the number embeddings lead to improved numerical reasoning accuracy and performance in DROP, a numerical QA dataset.

The semantic matching capabilities of neural information retrieval can ameliorate synonymy and polysemy problems of symbolic approaches. However, neural models’ dense representations are more suitable for re-ranking, due to their inefficiency. Sparse representations, either in symbolic or latent form, are more efficient with an inverted index. Taking the merits of the sparse and dense representations, we propose an ultra-high dimensional (UHD) representation scheme equipped with directly controllable sparsity. UHD’s large capacity and minimal noise and interference among the dimensions allow for binarized representations, which are highly efficient for storage and search. Also proposed is a bucketing method, where the embeddings from multiple layers of BERT are selected/merged to represent diverse linguistic aspects. We test our models with MS MARCO and TREC CAR, showing that our models outperforms other sparse models.

Numerical reasoning in machine reading comprehension (MRC) has shown drastic improvements over the past few years. While the previous models for numerical MRC are able to interpolate the learned numerical reasoning capabilities, it is not clear whether they can perform just as well on numbers unseen in the training dataset. Our work rigorously tests state-of-the-art models on DROP, a numerical MRC dataset, to see if they can handle passages that contain out-of-range numbers. One of the key findings is that the models fail to extrapolate to unseen numbers. Presenting numbers as digit-by-digit input to the model, we also propose the E-digit number form that alleviates the lack of extrapolation in models and reveals the need to treat numbers differently from regular words in the text. Our work provides a valuable insight into the numerical MRC models and the way to represent number forms in MRC.

Advances in Question Answering (QA) research require additional datasets for new domains, languages, and types of questions, as well as for performance increases. Human creation of a QA dataset like SQuAD, however, is expensive. As an alternative, an unsupervised QA approach has been proposed so that QA training data can be generated automatically. However, the performance of unsupervised QA is much lower than that of supervised QA models. We identify two anomalies in the automatically generated questions and propose how they can be mitigated. We show our approach helps improve unsupervised QA significantly across a number of QA tasks.

Unsupervised question answering (UQA) has been proposed to avoid the high cost of creating high-quality datasets for QA. One approach to UQA is to train a QA model with questions generated automatically. However, the generated questions are either too similar to a word sequence in the context or too drifted from the semantics of the context, thereby making it difficult to train a robust QA model. We propose a novel regularization method based on teacher-student architecture to avoid bias toward a particular question generation strategy and modulate the process of generating individual words when a question is generated. Our experiments demonstrate that we have achieved the goal of generating higher-quality questions for UQA across diverse QA datasets and tasks. We also show that this method can be useful for creating a QA model with few-shot learning.

Open Information Extraction (Open IE) aims at generating entity-relation-entity triples from a large amount of text, aiming at capturing key semantics of the text. Given a triple, the relation expresses the type of semantic relation between the entities. Although relations from an Open IE system are more extensible than those used in a traditional Information Extraction system and a Knowledge Base (KB) such as Knowledge Graphs, the former lacks in semantics; an Open IE relation is simply a sequence of words, whereas a KB relation has a predefined meaning. As a way to provide a meaning to an Open IE relation, we attempt to align it with one of the predefined set of relations used in a KB. Our approach is to use a Siamese network that compares two sequences of word embeddings representing an Open IE relation and a predefined KB relation. In order to make the approach practical, we automatically generate a training dataset using a distant supervision approach instead of relying on a hand-labeled dataset. Our experiment shows that the proposed method can capture the relational semantics better than the recent approaches.