Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2505.11924

Explaining Intrinsic Moral Self-Correction with Mechanistic Interpretability

Yu-Ting Lee·Fu-Chieh Chang·Yu-En Shu·Hui-Ying Shih·Pei-Yuan Wu
View original source ↗Read source document ↗Export metadata ↓

Abstract

Intrinsic moral self-correction refers to the phenomenon where a language model refines its ethical judgments or aligns its outputs purely through prompting. While effective across diverse tasks, its mechanism remains unclear. We hypothesize intrinsic moral self-correction functions by steering hidden representations along interpretable latent directions. Evaluating six LLMs across four morality-related tasks, we demonstrate that the representation shifts induced by self-correction prompts align with contrastive steering vectors. This alignment transfers even when the steering vectors are constructed from a disjoint corpus. Notably, when applied via activation addition, these prompt-induced shifts can alter model behavior more effectively than the self-correction prompts and the steering vectors. Our findings suggest representation steering is the mechanistic driver of intrinsic moral self-correction.

Explore related subjects

cs.CLcs.AIcs.LG

Keep this discovery

BibTeXRIS

Yu-Ting Lee, Fu-Chieh Chang, Yu-En Shu, Hui-Ying Shih, Pei-Yuan Wu. 2025-05-17. Explaining Intrinsic Moral Self-Correction with Mechanistic Interpretability. https://arxiv.org/abs/2505.11924

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Auto-RecSys: Harnessing Autonomous Research Agents for Industry-Scale Recommender System

Auto-research agents have shown the potential to automate hypothesis generation, experiment execution, and iterative refinement. However, scaling this paradigm to industry-scale recommendation models introduces two challenges: (1) long feedback loops, where model training can take days, making serial iteration prohibitively slow and requiring parallel exploration across multiple research directions; and (2) system complexity, where large configurations, fragile infrastructure dependencies, and multi-day GPU jobs require robust and recoverable execution. We present Auto-RecSys, an autonomous research system for long-horizon experimentation on industry-scale recommendation models. Auto-RecSys addresses these challenges through three harness designs: (1) distributed asynchronous execution for running multiple experiments in parallel across servers, (2) centralized cross-server memory for persistent and recoverable execution across sessions and failures, and (3) cognitive-procedural separation, where natural-language skill files guide LLM reasoning while deterministic scripts enforce operational correctness. Auto-RecSys further employs a dual-loop self-evolving architecture: an Execution Evolution Loop in which model-specific playbooks accumulate operational knowledge by recording failed attempts and crystallizing successful pipelines, and an Idea Evolution Loop in which experimental outcomes inform subsequent ideation. Evaluated on recommendation models, Auto-RecSys significantly reduces the human time required per experiment cycle and improves execution reliability as its playbooks mature.

cs.CL↗
arXiv2026

Structurally Speaking: Motif-Oriented Graph Captioning through Bidirectional Graph-Text Translation

Graph captions should help readers understand graph structure, rather than simply translate adjacency matrices into long textual edge lists. A useful graph caption abstracts connectivity into recognizable motifs, such as hubs, paths, cycles, cliques, and bridges, because these motifs provide compact structural units that are easier to read, compare, and recover. In this paper, we study motif-oriented graph captioning as a bidirectional graph-text translation task, where captions must both preserve enough topology for graph recovery and express the graph through concise motif-level descriptions. We show that direct prompting of GPT-5.1 often produces graph-recoverable captions by enumerating node-to-node connections, but these captions are verbose and can contain inconsistent motif interpretations. To address this gap, we introduce Structurally Speaking, a lightweight structured prompting protocol that guides translation between explicit connectivity and motif-level abstraction. Experiments on a synthetic motif-based dataset show that structured prompting produces shorter and more motif-consistent captions while maintaining comparable graph recovery. These results suggest that explicit topology-to-motif reasoning guidance can make LLM-generated graph captions more interpretable without model fine-tuning.

cs.CL↗
arXiv2026

Using Semantic Uncertainty to Estimate Transition Relevance in Turn-taking

Turn-taking is a fundamental mechanism that governs when interlocutors speak and listen. Although Spoken Dialogue Systems (SDS) exploit a range of linguistic, acoustic, and non-verbal cues, they produce ill-timed responses in unscripted interaction. A central challenge is anticipating Transition Relevance Places (TRPs), or opportunities, not obligations, for a listener to take the floor. Human listeners do not wait for turn endings; as an utterance unfolds, they use expectations about its developing meaning to anticipate TRPs and decide whether to take the floor. We examine whether these evolving expectations can be modeled through semantic uncertainty -- an LLM-derived measure of how strongly a turn so far constrains what may plausibly come next. To do so, we sample possible continuations of an ongoing turn and use changes in semantic dispersion to identify TRPs within turns. We evaluate this account on a dataset with TRP labels derived from real-time listener responses, rather than retrospective annotation. Our approach substantially outperforms prompt-based and fine-tuned text-only baselines, providing empirical support for the view that evolving semantic constraints inform perceived turn-taking opportunities in unscripted interaction.

cs.CL↗