Formalizing the Moral Evaluation of Speech Acts: Truthfulness, Lies and Ethical Dilemmas

Benjamin Icard; Gauvain Bourgne; Jeanne Bonnaventure; Jean-Gabriel Ganascia

cs.AIOct 3, 2026

Formalizing the Moral Evaluation of Speech Acts: Truthfulness, Lies and Ethical Dilemmas

Authors: Benjamin Icard, Gauvain Bourgne, Jeanne Bonnaventure, Jean-Gabriel Ganascia

Organizations: LIP6, Sorbonne University, CNRS, France

Abstract

In life-or-death situations, a benevolent lie may appear more moral than telling the truth. Yet such lies can backfire, producing unintended and sometimes fatal consequences. This tension, famously disputed by Kant and Constant in 1797, applies not only to lying but to assertive speech acts in general, raising the question of which utterance should be chosen when moral stakes are high. We present a logical framework for the ethical evaluation of speech-act utterances based on agents' beliefs. Implemented in Answer Set Programming (ASP), the framework assesses utterances under deontologism, consequentialism, and principialism, and is illustrated on Sartre's The Wall (1939), a reworking of that controversy in which lying leads alternately to rescue and to death. Our setting is general by design: as two variants show, accommodating a new moral situation amounts to adjusting parameters, not rules.

Figures & tables

Speaker’s Intention	Content of the Utterance
Speaker’s Intention	True	False
Honest	objective truth	erroneous truth
Dishonest	erroneous lie	objective lie

Table 1: Epistemic types of speech acts based on the speaker’s communicative intention and the content of their utterances.

Utterance	Pablo’s Plan		Outcome	Deontologism			Principialism		Consequentialism
Utterance	Intention	Motive	For Ramon	m1	m2	m1+2	p1	p2	c1	c2
	Type of Evaluation			Absolute			Local	Global	Anticipations	Reality
objective_truth	Honest	Maleficent	Detrimental	✗	✓	✗	✗	✗	✗	✗
erroneous_truth	Honest	Maleficent	Beneficial	✗	✓	✗	✗	✗	✗	✓
objective_lie	Dishonest	Benevolent	Beneficial	✓	✗	✗	✓	✓	✓	✓
erroneous_lie	Dishonest	Benevolent	Detrimental	✓	✗	✗	✓	✓	✓	✗

Table 2: Moral evaluation of Pablo’s speech-act options in Sartre’s The Wall , where m , p , c abbreviate maxim , principialism , consequentialism ; with ✓ : permissible, and ✗ : impermissible. NB : here, verdicts assume no better alternative (silence, evasion) is available to Pablo.

Moral Reasoning

Moral reasoning studies how people and AI systems interpret ethical principles, weigh competing values, and justify judgments in context.

See all 45 papers

Is LLM's Moral Decision Compositional?
May 29, 2026Weijia Zhang, Ruiqi Chen, Yunze Xiao +1LLM Evaluation Moral Reasoning in Language Models
University of Illinois Urbana-Champaign · University of Michigan · Carnegie Mellon University +1
Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment
Sep 18, 2026Maciej SkorskiAnnotator Disagreement Algorithmic Auditing
University of Luxembourg
LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models
Mar 6, 2026Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck +5Deception in Language Models Language Model Safety Evaluation
Oracle · Intel Labs · Oregon State University +2

May 29, 2026J/K move · Enter open · S save

Is LLM's Moral Decision Compositional?

Weijia Zhang, Ruiqi Chen, Yunze Xiao, Weihao Xuan

University of Illinois Urbana-Champaign · University of Michigan · Carnegie Mellon University+1

LLM Evaluation Moral Reasoning in Language Models Moral Reasoning

Open paper AskPDF arXiv

Moral evaluations of language models typically infer a model's values from its choices between single acts, yet in everyday life a person is judged on their history of good and bad acts. Such evaluations cannot capture how a model combines one person's acts. We test whether a model's moral judgment is compositional, that is, whether its judgment of a person follows from its judgments of each act. We introduce Moral Composition Arena, which asks which of two people is morally better to give Elo ratings to 229 human-validated acts across five Moral Foundations Theory foundations (act Elo) and to 160 controlled composite profiles, each a person described by two acts (composite Elo). Across ten frontier models and 29,134 choices, summed act Elo explains 73% of the variance in composite Elo, but the composition rule is not additive. With nearly equal mean summed act Elo, one extreme virtue with a minor wrong outranks two minor virtues in every model (mean +35.0 Elo), an extremity premium that survives a nonlinear baseline and human relabeling of act intensities. Single-act evaluations thus predict most of how these models judge people described by two acts, but miss a systematic premium on extreme acts.

Abstract

Moral Reasoning

Explore similar work

Is LLM's Moral Decision Compositional?

Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment

LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models