We introduce MiRAGE, an evaluation framework for retrieval-augmented generation (RAG) from multimodal sources. As audiovisual media becomes a prevalent source of information online, it is essential for RAG systems to integrate information from these sources into generation. However, existing evaluations for RAG are text-centric, limiting their applicability to multimodal, reasoning intensive settings because they don't verify information against sources. MiRAGE is a claim-centric approach to multimodal RAG evaluation, consisting of InfoF1, evaluating factuality and information coverage, and CiteF1, measuring citation support and completeness. We show that MiRAGE, when applied by humans, strongly aligns with extrinsic quality judgments. We additionally introduce automatic variants of MiRAGE and three prominent TextRAG metrics -- ACLE, ARGUE, and RAGAS -- demonstrating the limitations of text-centric work and laying the groundwork for automatic evaluation. We release open-source implementations and outline how to assess multimodal RAG.

Wikipedia is a critical resource for modern NLP, serving as a rich repository of up-to-date and citation-backed information on a wide variety of subjects. The reliability of Wikipedia -- its groundedness in its cited sources -- is vital to this purpose. This work analyzes both how grounded Wikipedia is and how readily fine-grained grounding evidence can be retrieved. To this end, we introduce PeopleProfiles -- a large-scale, multi-level dataset of claim support annotations on biographical Wikipedia articles. We show that: (1) ~22% of claims in Wikipedia lead sections are unsupported by the article body; (2) ~30% of claims in the article body are unsupported by their publicly accessible sources; and (3) real-world Wikipedia citation practices often differ from documented standards. Finally, we show that complex evidence retrieval remains a challenge -- even for recent reasoning rerankers.

Existing methods for evaluating the factuality of large language model (LLM) responses treat all claims as equally important. This results in misleading evaluations when vital information is missing or incorrect as it receives the same weight as peripheral details, raising the question: how can we reliably detect such differences when there are errors in key information? Current approaches that measure factuality tend to be insensitive to omitted or false key information. To investigate this lack of sensitivity, we construct VITALERRORS, a benchmark of 6,733 queries with minimally altered LLM responses designed to omit or falsify key information. Using this dataset, we demonstrate the insensitivities of existing evaluation metrics to key information errors. To address this gap, we introduce VITAL, a set of metrics that provide greater sensitivity in measuring the factuality of responses by incorporating the relevance and importance of claims with respect to the query. Our analysis demonstrates that VITAL metrics more reliably detect errors in key information than previous methods. Our dataset, metrics, and analysis provide a foundation for more accurate and robust assessment of LLM factuality.

The rapid spread of misinformation in the digital era poses significant challenges to public discourse, necessitating robust and scalable fact-checking solutions. Traditional human-led fact-checking methods, while credible, struggle with the volume and velocity of online content, prompting the integration of automated systems powered by Large Language Models (LLMs). However, existing automated approaches often face limitations, such as handling complex claims, ensuring source credibility, and maintaining transparency. This paper proposes a novel multi-agent system for automated fact-checking that enhances accuracy, efficiency, and explainability. The system comprises four specialized agents: an Input Ingestion Agent for claim decomposition, a Query Generation Agent for formulating targeted subqueries, an Evidence Retrieval Agent for sourcing credible evidence, and a Verdict Prediction Agent for synthesizing veracity judgments with human-interpretable explanations. Evaluated on benchmark datasets (FEVEROUS, HOVER, SciFact), the proposed system achieves a 12.3% improvement in Macro F1-score over baseline methods. The system effectively decomposes complex claims, retrieves reliable evidence from trusted sources, and generates transparent explanations for verification decisions. Our approach contributes to the growing field of automated fact-checking by providing a more accurate, efficient, and transparent verification methodology that aligns with human fact-checking practices while maintaining scalability for real-world applications. Our source code is available at https://github.com/HySonLab/FactAgent

Training powerful AI systems to exhibit desired behaviors hinges on the ability to provide accurate human supervision on increasingly complex tasks. A promising approach to this problem is to amplify human judgement by leveraging the power of two competing AIs in a debate about the correct solution to a given problem. Prior theoretical work has provided a complexity-theoretic formalization of AI debate, and posed the problem of designing protocols for AI debate that guarantee the correctness of human judgements for as complex a class of problems as possible. Recursive debates, in which debaters decompose a complex problem into simpler subproblems, hold promise for growing the class of problems that can be accurately judged in a debate. However, existing protocols for recursive debate run into the obfuscated arguments problem: a dishonest debater can use a computationally efficient strategy that forces an honest opponent to solve a computationally intractable problem to win. We mitigate this problem with a new recursive debate protocol that, under certain stability assumptions, ensures that an honest debater can win with a strategy requiring computational efficiency comparable to their opponent.

If AI systems match or exceed human capabilities on a wide range of tasks, it may become difficult for humans to efficiently judge their actions -- making it hard to use human feedback to steer them towards desirable traits. One proposed solution is to leverage another superhuman system to point out flaws in the system's outputs via a debate. This paper outlines the value of debate for AI safety, as well as the assumptions and further research required to make debate work. It does so by sketching an ``alignment safety case'' -- an argument that an AI system will not autonomously take actions which could lead to egregious harm, despite being able to do so. The sketch focuses on the risk of an AI R\&D agent inside an AI company sabotaging research, for example by producing false results. To prevent this, the agent is trained via debate, subject to exploration guarantees, to teach the system to be honest. Honesty is maintained throughout deployment via online training. The safety case rests on four key claims: (1) the agent has become good at the debate game, (2) good performance in the debate game implies that the system is mostly honest, (3) the system will not become significantly less honest during deployment, and (4) the deployment context is tolerant of some errors. We identify open research problems that, if solved, could render this a compelling argument that an AI system is safe.

Language models are increasingly being used in important decision pipelines, so ensuring the correctness of their outputs is crucial. Recent work has proposed evaluating the "factuality" of claims decomposed from a language model generation and applying conformal prediction techniques to filter out those claims that are not factual. This can be effective for tasks such as information retrieval, where constituent claims may be evaluated in isolation for factuality, but is not appropriate for reasoning tasks, as steps of a logical argument can be evaluated for correctness only within the context of the claims that precede them. To capture this, we define "coherent factuality" and develop a conformal-prediction-based method to guarantee coherent factuality for language model outputs. Our approach applies split conformal prediction to subgraphs within a "deducibility" graph" that represents the steps of a reasoning problem. We evaluate our method on mathematical reasoning problems from the MATH and FELM datasets and find that our algorithm consistently produces correct and substantiated orderings of claims, achieving coherent factuality across target coverage levels. Moreover, we achieve 90% factuality on our stricter definition while retaining 80% or more of the original claims, highlighting the utility of our deducibility-graph-guided approach.

Current research on the \textit{Decompose-Then-Verify} paradigm for evaluating the factuality of long-form text typically treats decomposition and verification in isolation, overlooking their interactions and potential misalignment. We find that existing decomposition policies, typically hand-crafted demonstrations, do not align well with downstream verifiers in terms of atomicity -- a novel metric quantifying information density -- leading to suboptimal verification results. We formulate finding the optimal decomposition policy for optimal verification as a bilevel optimization problem. To approximate a solution for this strongly NP-hard problem, we propose dynamic decomposition, a reinforcement learning framework that leverages verifier feedback to learn a policy for dynamically decomposing claims to verifier-preferred atomicity. Experimental results show that dynamic decomposition outperforms existing decomposition policies, improving verification confidence by 0.07 and accuracy by 0.12 (on a 0-1 scale) on average across varying verifiers, datasets, and atomcities of input claims.

The decompose-then-verify strategy for verification of Large Language Model (LLM) generations decomposes claims that are then independently verified. Decontextualization augments text (claims) to ensure it can be verified outside of the original context, enabling reliable verification. While decomposition and decontextualization have been explored independently, their interactions in a complete system have not been investigated. Their conflicting purposes can create tensions: decomposition isolates atomic facts while decontextualization inserts relevant information. Furthermore, a decontextualized subclaim presents a challenge to the verification step: what part of the augmented text should be verified as it now contains multiple atomic facts? We conduct an evaluation of different decomposition, decontextualization, and verification strategies and find that the choice of strategy matters in the resulting factuality scores. Additionally, we introduce DnDScore, a decontextualization aware verification method which validates subclaims in the context of contextual information.

Hallucinations -- the generation of untrue claims -- pose a challenge to the application of large language models (LLMs) [1] thereby motivating the development of metrics to evaluate factual precision. We observe that popular metrics using the Decompose-Then-Verify framework, such as FActScore [2], can be manipulated by adding obvious or repetitive claims to artificially inflate scores. We expand the FActScore dataset to design and analyze factual precision metrics, demonstrating that models can be trained to achieve high scores under existing metrics through exploiting the issues we identify. This motivates our new customizable plug-and-play subclaim selection component called Core, which filters down individual subclaims according to their uniqueness and informativeness. Metrics augmented by Core are substantially more robust as shown in head-to-head comparisons. We release an evaluation framework supporting the modular use of Core (https://github.com/zipJiang/Core) and various decomposition strategies, and we suggest its adoption by the LLM community. [1] Hong et al., "The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models", arXiv:2404.05904v2 [cs.CL]. [2] Min et al., "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation", arXiv:2305.14251v2 [cs.CL].