acceptodds
Desk rejected at ICLR 2027

Reasoning or Just Prompting? Probing the Mechanism of Latent Chemical Reasoning

Desk rejected at ICLR 2027, so left out of the paper lists and the map.

Abstract

Latent reasoning performs intermediate computation in continuous space rather than through explicit tokens, which is particularly appealing in chemistry, where errors in explicit reasoning can propagate to the final answer. Yet if latent states truly constitute an implicit reasoning chain, they should be causally important. We find otherwise: swapping or perturbing intermediate latent states has little effect on performance, while removing them entirely sometimes causes a substantial score drop. Thus, the latent states matter, but the trajectory they form appears to matter far less. This points to a simpler interpretation. Rather than encoding a step-by-step reasoning chain, latent states may primarily steer subsequent model computation, much like soft prompts. Indeed, a single fixed prefix shared across molecules reproduces LatentChem’s performance, and a learned static soft prompt performs comparably to per-input latent generation in controlled models. The tolerance of latent sequences to substitution and moderate perturbation further supports this connection. We therefore suggest that latent chemical reasoning may be better viewed as soft prompting than as a reasoning chain hidden in continuous space.

Primary area:
interpretability and explainable AI
Keywords:
latent reasoning, chemical reasoning, soft prompting, causal interventions, interpretability

Related papers

Discussion (0)

Sign in to comment.