# The Point of No Return: Counterfactual Localization of Deceptive Commitment in Language-Model Reasoning

arXiv: https://arxiv.org/abs/2605.17113 · HTML: https://mlsanity.com/paper/2605.17113/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 13 of its 36 references that are in the map.
- First posted on arXiv 16 May 2026.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 13 of 13)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [ShieldGemma: Generative AI Content Moderation Based on Gemma](https://mlsanity.com/paper/2407.21772/) (2024)
- [Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias](https://mlsanity.com/paper/2004.12265/) (2020)
- [Large Language Models can Strategically Deceive their Users when Put Under Pressure](https://mlsanity.com/paper/2311.07590/) (2023)
- [Thought Anchors: Which LLM Reasoning Steps Matter?](https://mlsanity.com/paper/2506.19143/) (2025)
- [Liars' Bench: Evaluating Lie Detectors for Language Models](https://mlsanity.com/paper/2511.16035/) (2025)
- [Activation Steering via Generative Causal Mediation](https://mlsanity.com/paper/2602.16080/) (2026)
- [UNIDECOR: A Unified Deception Corpus for Cross-Corpus Deception Detection](https://mlsanity.com/paper/2306.02827/) (2023)

## Built on by (most cited first, 1 of 1)

- [It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories](https://mlsanity.com/paper/2609.03436/) (2026)

## Abstract (arXiv)

Existing deception datasets label completed outputs as honest or deceptive, treating deception as a property of the final response rather than a function of the model's reasoning trace. This obscures a more fundamental question: when does a language model become committed to deception? We introduce counterfactual localization: for each sentence prefix in a reasoning trace, we fix the prefix, resample continuations, and estimate the probability of a deceptive outcome. To scale this, we construct five environments (spanning strategic bluffing, maze guidance, financial advice, used-car sales, and offer negotiation) in which deception is never prompted but emerges from strategic incentives and labels follow mechanically from environment state rather than subjective human judgment. The resulting corpus localizes ~1.46M sentences across four reasoning models, drawn from over 94.1M sampled continuations, 91.5B generated tokens, and over 100K scenarios. Sentence-level human evaluation confirms that detected commitment points correspond to interpretable shifts in decision state. Using this resource, we show that lexical cues for commitment prediction transfer poorly across environments, whereas attention-based transition features generalize out of distribution, suggesting that deceptive commitment is reflected in reusable changes in reasoning dynamics rather than surface form. We further identify compact attention-head sets (under 10% of heads) that, selected on one environment, causally suppress deceptive commitment across held-out environments. We release the corpus as a substrate for studying deception, and more broadly commitment, in language-model reasoning.