# Human-AI Co-Interpretation for Responsible AI: A Hermeneutic Perspective

arXiv: https://arxiv.org/abs/2609.00334 · HTML: https://mlsanity.com/paper/2609.00334/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 82 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Builds on (most cited first, 26 of 26)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models](https://mlsanity.com/paper/2310.00746/) (2023)
- [Rethinking Interpretability in the Era of Large Language Models](https://mlsanity.com/paper/2402.01761/) (2024)
- [Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations](https://mlsanity.com/paper/2310.11207/) (2023)
- [Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary](https://mlsanity.com/paper/2010.00490/) (2020)
- [Question Answering as an Automatic Evaluation Metric for News Article Summarization](https://mlsanity.com/paper/1906.00318/) (2019)
- [Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory](https://mlsanity.com/paper/1809.05296/) (2018)
- [Societal Alignment Frameworks Can Improve LLM Alignment](https://mlsanity.com/paper/2503.00069/) (2025)
- [Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI Alignment](https://mlsanity.com/paper/2604.10673/) (2026)
- [Language Models as Semiotic Machines: Reconceptualizing AI Language Systems through Structuralist and Post-Structuralist Theories of Language](https://mlsanity.com/paper/2410.13065/) (2024)

## Abstract (arXiv)

Across law, education, policy analysis, and public moral argumentation, LLM outputs are being used often for work that requires interpretations to be justified with textual evidence and explicit normative standards. Yet a recurrent failure mode -- what I call textitinterpretive misplacement -- is that model-generated readings get treated as settled meanings without an explicit interpretive frame (sources, scope constraints, normative commitments), without preserving defensible alternatives, and without provenance that lets readers find the supporting passages. In such settings, the risk is not only factual error but lost accountability: readers and institutions cannot reliably assess what an output commits them to, or on what basis. Drawing on philosophical hermeneutics, this paper discusses this risk and derives design principles for structuring human-AI co-interpretation. The paper also provides a structured synthesis of recent scholarship on hermeneutics and AI, organizing this emerging literature into a set of recurrent lines of argument and design-relevant gaps. LLM outputs are treated as candidate readings, whereas hermeneutic understanding is reserved for accountable human interpreters situated in disciplinary historical-linguistic traditions. Human-AI interaction is characterized as an AI-mediated interpretive loop. Hermeneutic understanding is distinguished from token-prediction--based text generation. On this basis, existing LLM techniques are reorganized into design patterns for hermeneutically responsible use in interpretive settings. Finally, the discussion turns to implications for legal practice, educational assessment and feedback, scholarly knowledge production, and public moral argumentation. It also treats digital hermeneutics as a literacy: the capacity to read AI-mediated texts by examining frames, provenance, and readings, and by contesting outputs.