Pith. sign in

REVIEW 8 cited by

Can LLMs Follow Simple Rules?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.04235 v3 pith:5RC57MVH submitted 2023-11-06 cs.AI cs.CLcs.LG

Can LLMs Follow Simple Rules?

classification cs.AI cs.CLcs.LG
keywords rulesllmsmodelmodelssimpleattackscasesevaluation
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

As Large Language Models (LLMs) are deployed with increasing real-world responsibilities, it is important to be able to specify and constrain the behavior of these systems in a reliable manner. Model developers may wish to set explicit rules for the model, such as "do not generate abusive content", but these may be circumvented by jailbreaking techniques. Existing evaluations of adversarial attacks and defenses on LLMs generally require either expensive manual review or unreliable heuristic checks. To address this issue, we propose Rule-following Language Evaluation Scenarios (RuLES), a programmatic framework for measuring rule-following ability in LLMs. RuLES consists of 14 simple text scenarios in which the model is instructed to obey various rules while interacting with the user. Each scenario has a programmatic evaluation function to determine whether the model has broken any rules in a conversation. Our evaluations of proprietary and open models show that almost all current models struggle to follow scenario rules, even on straightforward test cases. We also demonstrate that simple optimization attacks suffice to significantly increase failure rates on test cases. We conclude by exploring two potential avenues for improvement: test-time steering and supervised fine-tuning.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

    cs.CR 2024-06 unverdicted novelty 8.0

    AgentDojo introduces an extensible evaluation framework populated with realistic agent tasks and security test cases to measure prompt injection robustness in tool-using LLM agents.

  2. Scale-Dependent Collective Adaptation in Self-Amending LLM Societies: A Cross-Family Study of Emergent Governance

    nlin.AO 2026-05 unverdicted novelty 7.0

    LLM societies in Nomic show non-monotonic collective adaptation peaking at mid-scales, with smaller models rule-inert and larger ones restrictive.

  3. Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense

    cs.CR 2026-06 unverdicted novelty 6.0

    Prompt injection defenses create a security-fidelity tradeoff with no model or defense achieving both high security and high fidelity on the SecFid benchmark across 1,168 examples.

  4. LLM-as-Code: Agentic Programming for Agent Harness

    cs.AI 2026-06 unverdicted novelty 6.0

    Proposes Agentic Programming in which programs control execution flow and LLMs act as invoked components (LLM-as-Code) only for reasoning, producing DAG-structured contexts that improve stability in long-horizon compu...

  5. Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies

    cs.CL 2026-04 unverdicted novelty 6.0

    LLMs display systematic, architecture-dependent gaps between their self-stated safety policies and observed behavior on harmful prompts, with absolute refusal claims frequently violated.

  6. Engineering Trustworthy Agentic AI for Critical Systems

    cs.AI 2026-07 conditional novelty 5.0

    A survey claiming that agentic AI trustworthiness is a single cross-domain problem and outlining a framework for graded, certifiable assurance.

  7. Prompt Governance? On Governing Technologies Governed by Natural Language

    cs.CY 2026-04 unverdicted novelty 4.0

    Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.

  8. Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption

    cs.CR 2025-10 unverdicted novelty 4.0

    LLM watermarking adoption is limited by misaligned stakeholder incentives; incentive-aligned approaches such as in-context watermarking can enable practical use in targeted domains like education and peer review.