Recent advancements in Large Language Models (LLMs) have heralded unprecedented capabilities in information-seeking and text generation, as evidenced by applications like Bing Chat and perplexity.ai. Despite these strides, challenges on hallucination and factual inconsistency continue to impede their wider real-world adoption. Contemporary methods, including retrieval-augmented LLMs and feedback-based learning, serve as alternatives to mitigate these challenges. However, challenges remain, particularly regarding referencing erroneous evidence (citation errors) and generating information not present in the evidence (hallucination). In this paper, we introduce the 𝖠²𝖱 framework: Ask, Assess, and Refine. Our approach utilizes an explicit evaluation paradigm, incorporating metrics specifically tailored to assess citation errors and hallucination, aiming to address these prevalent challenges robustly. Capitalizing on these evaluations, we devise a strategy to formulate actionable natural language feedback, enabling iterative refinements that yield improved factual consistency and reduced hallucinations in responses. Our experiments on ASQA, ELI5, and QAMPARI datasets demonstrate our method’s superiority in enhancing correctness, fluency, and citation quality.

Transformer-based models for question answering (QA) over tables and texts confront a “long” hybrid sequence over tabular and textual elements, causing long-range reasoning problems. To handle long-range reasoning, we extensively employ a fusion-in-decoder (FiD) and exponential moving average (EMA), proposing a Moving Average Equipped Fusion-in-Decoder (MAFiD). With FiD as the backbone architecture, MAFiD combines various levels of reasoning: independent encoding of homogeneous data and single-row and multi-row heterogeneous reasoning, using a gated cross attention layer to effectively aggregate the three types of representations resulting from various reasonings. Experimental results on HybridQA indicate that MAFiD achieves state-of-the-art performance by increasing exact matching (EM) and F1 by 1.1 and 1.7, respectively, on the blind test set.

In this study, we examine the ability of contextualized representations of pretrained language model to distinguish whether sequences from instructional articles are plausible or implausible. Towards this end, we compare the BERT, RoBERTa, and DeBERTa models using simple classifiers based on the sentence representations of the [CLS] tokens and perform a detailed analysis by visualizing the representations of the [CLS] tokens of the models. In the experimental results of Subtask A: Multi-Class Classification, DeBERTa exhibits the best performance and produces a more distinguishable representation across different labels. Submitting an ensemble of 10 DeBERTa-based models, our final system achieves an accuracy of 61.4% and is ranked fifth out of models submitted by eight teams. Further in-depth results suggest that the abilities of pretrained language models for the plausibility detection task are more strongly affected by their model structures or attention designs than by their model sizes.

This study proposes Semantic-Infused SElective Graph Reasoning (SISER) for fact verification, which newly presents semantic-level graph reasoning and injects its reasoning-enhanced representation into other types of graph-based and sequence-based reasoning methods. SISER combines three reasoning types: 1) semantic-level graph reasoning, which uses a semantic graph from evidence sentences, whose nodes are elements of a triple – <Subject, Verb, Object>, 2) “semantic-infused” sentence-level “selective” graph reasoning, which combine semantic-level and sentence-level representations and perform graph reasoning in a selective manner using the node selection mechanism, and 3) sequence reasoning, which concatenates all evidence sentences and performs attention-based reasoning. Experiment results on a large-scale dataset for Fact Extraction and VERification (FEVER) show that SISER outperforms the previous graph-based approaches and achieves state-of-the-art performance.

LM-BFF (CITATION) achieves significant few-shot performance by using auto-generated prompts and adding demonstrations similar to an input example. To improve the approach of LM-BFF, this paper proposes LM-BFF-MS—better few-shot fine-tuning of language models with multiple soft demonstrations by making its further extensions, which include 1) prompts with multiple demonstrations based on automatic generation of multiple label words; and 2) soft demonstration memory which consists of multiple sequences of globally shared word embeddings for a similar context. Experiments conducted on eight NLP tasks show that LM-BFF-MS leads to improvements over LM-BFF on five tasks, particularly achieving 94.0 and 90.4 on SST-2 and MRPC, respectively.