While Large Language Models (LLMs) can generate fluent and convincing responses, they are not necessarily correct. This is especially apparent in the popular decompose-then-verify factuality evaluation pipeline, where LLMs evaluate generations by decomposing the generations into individual, valid claims. Factuality evaluation is especially important for medical answers, since incorrect medical information could seriously harm the patient. However, existing factuality systems are a poor match for the medical domain, as they are typically only evaluated on objective, entity-centric, formulaic texts such as biographies and historical topics. This differs from condition-dependent, conversational, hypothetical, sentence-structure diverse, and subjective medical answers, which makes decomposition into valid facts challenging. We propose MedScore, a new pipeline to decompose medical answers into condition-aware valid facts and verify against in-domain corpora. Our method extracts up to three times more valid facts than existing methods, reducing hallucination and vague references, and retaining condition-dependency in facts. The resulting factuality score substantially varies by decomposition method, verification corpus, and used backbone LLM, highlighting the importance of customizing each step for reliable factuality evaluation by using our generalizable and modularized pipeline for domain adaptation.

Language models can be sampled multiple times to access the distribution underlying their responses, but existing methods cannot efficiently synthesize rich epistemic signals across different long-form responses. We introduce Consensus Graphs (ConGrs), a flexible DAG-based data structure that represents shared information, as well as semantic variation in a set of sampled LM responses to the same prompt. We construct ConGrs using a light-weight lexical sequence alignment algorithm from bioinformatics, supplemented by the targeted usage of a secondary LM judge. Further, we design task-dependent decoding methods to synthesize a single, final response from our ConGr data structure. Our experiments show that synthesizing responses from ConGrs improves factual precision on two biography generation tasks by up to 31% over an average response and reduces reliance on LM judges by more than 80% compared to other methods. We also use ConGrs for three refusal-based tasks requiring abstention on unanswerable queries and find that abstention rate is increased by up to 56%. We apply our approach to the MATH and AIME reasoning tasks and find an improvement over self-verification and majority vote baselines by up to 6 points of accuracy. We show that ConGrs provide a flexible method for capturing variation in LM responses and using the epistemic signals provided by response variation to synthesize more effective responses.

Large Language Models (LLMs) excel in fluency but risk producing inaccurate content, called "hallucinations." This paper outlines a standardized process for categorizing fine-grained hallucination types and proposes an innovative framework--the Progressive Fine-grained Model Editor (PFME)--specifically designed to detect and correct fine-grained hallucinations in LLMs. PFME consists of two collaborative modules: the Real-time Fact Retrieval Module and the Fine-grained Hallucination Detection and Editing Module. The former identifies key entities in the document and retrieves the latest factual evidence from credible sources. The latter further segments the document into sentence-level text and, based on relevant evidence and previously edited context, identifies, locates, and edits each sentence's hallucination type. Experimental results on FavaBench and FActScore demonstrate that PFME outperforms existing methods in fine-grained hallucination detection tasks. Particularly, when using the Llama3-8B-Instruct model, PFME's performance in fine-grained hallucination detection with external knowledge assistance improves by 8.7 percentage points (pp) compared to ChatGPT. In editing tasks, PFME further enhances the FActScore of FActScore-Alpaca13B and FActScore-ChatGPT datasets, increasing by 16.2pp and 4.6pp, respectively.

FActScore has gained popularity as a metric to estimate the factuality of long-form texts generated by Large Language Models (LLMs) in English. However, there has not been any work in studying the behavior of FActScore in other languages. This paper studies the limitations of each component in the four-component pipeline of FActScore in the multilingual setting. We introduce a new dataset for FActScore on texts generated by strong multilingual LLMs. Our evaluation shows that LLMs exhibit distinct behaviors in both fact extraction and fact scoring tasks. No LLM produces consistent and reliable FActScore across languages with varying levels of resources. We also find that the knowledge source plays an important role in the quality of the estimated FActScore. Using Wikipedia as the knowledge source may hinder the true FActScore of long-form text due to its limited coverage in medium- and low-resource languages. We also incorporate three mitigations to our knowledge source that ultimately improve FActScore estimation across all languages.

Large language models (LLMs) are notorious for hallucinating, i.e., producing erroneous claims in their output. Such hallucinations can be dangerous, as occasional factual inaccuracies in the generated text might be obscured by the rest of the output being generally factually correct, making it extremely hard for the users to spot them. Current services that leverage LLMs usually do not provide any means for detecting unreliable generations. Here, we aim to bridge this gap. In particular, we propose a novel fact-checking and hallucination detection pipeline based on token-level uncertainty quantification. Uncertainty scores leverage information encapsulated in the output of a neural network or its layers to detect unreliable predictions, and we show that they can be used to fact-check the atomic claims in the LLM output. Moreover, we present a novel token-level uncertainty quantification method that removes the impact of uncertainty about what claim to generate on the current step and what surface form to use. Our method Claim Conditioned Probability (CCP) measures only the uncertainty of a particular claim value expressed by the model. Experiments on the task of biography generation demonstrate strong improvements for CCP compared to the baselines for seven LLMs and four languages. Human evaluation reveals that the fact-checking pipeline based on uncertainty quantification is competitive with a fact-checking tool that leverages external knowledge.

Knowledge Graph Question Answering (KGQA) methods seek to answer Natural Language questions using the relational information stored in Knowledge Graphs (KGs). With the recent advancements of Large Language Models (LLMs) and their remarkable reasoning abilities, there is a growing trend to leverage them for KGQA. However, existing methodologies have only focused on answering factual questions, e.g., "In which city was Silvio Berlusconi's first wife born?", leaving questions involving commonsense reasoning that real-world users may pose more often, e.g., "Do I need separate visas to see the Venus of Willendorf and attend the Olympics this summer?" unaddressed. In this work, we first observe that existing LLM-based methods for KGQA struggle with hallucination on such questions, especially on queries targeting long-tail entities (e.g., non-mainstream and recent entities), thus hindering their applicability in real-world applications especially since their reasoning processes are not easily verifiable. In response, we propose Right for Right Reasons (R3), a commonsense KGQA methodology that allows for a verifiable reasoning procedure by axiomatically surfacing intrinsic commonsense knowledge of LLMs and grounding every factual reasoning step on KG triples. Through experimental evaluations across three different tasks--question answering, claim verification, and preference matching--our findings showcase R3 as a superior approach, outperforming existing methodologies and notably reducing instances of hallucination and reasoning errors.

Large Language Models (LLMs) are prone to factuality hallucination, generating text that contradicts established knowledge. While extensive research has addressed this in English, little is known about multilingual LLMs. This paper systematically evaluates multilingual LLMs' factual accuracy across languages and geographic regions. We introduce a novel pipeline for multilingual factuality evaluation, adapting FActScore(Min et al., 2023) for diverse languages. Our analysis across nine languages reveals that English consistently outperforms others in factual accuracy and quantity of generated facts. Furthermore, multilingual models demonstrate a bias towards factual information from Western continents. These findings highlight the need for improved multilingual factuality assessment and underscore geographical biases in LLMs' fact generation.

Evaluating the factuality of long-form text generated by large language models (LMs) is non-trivial because (1) generations often contain a mixture of supported and unsupported pieces of information, making binary judgments of quality inadequate, and (2) human evaluation is time-consuming and costly. In this paper, we introduce FACTSCORE, a new evaluation that breaks a generation into a series of atomic facts and computes the percentage of atomic facts supported by a reliable knowledge source. We conduct an extensive human evaluation to obtain FACTSCOREs of people biographies generated by several state-of-the-art commercial LMs -- InstructGPT, ChatGPT, and the retrieval-augmented PerplexityAI -- and report new analysis demonstrating the need for such a fine-grained score (e.g., ChatGPT only achieves 58%). Since human evaluation is costly, we also introduce an automated model that estimates FACTSCORE using retrieval and a strong language model, with less than a 2% error rate. Finally, we use this automated metric to evaluate 6,500 generations from a new set of 13 recent LMs that would have cost $26K if evaluated by humans, with various findings: GPT-4 and ChatGPT are more factual than public models, and Vicuna and Alpaca are some of the best public models. FACTSCORE is available for public use via `pip install factscore`.