Pith. sign in

REVIEW 9 cited by

Following Length Constraints in Instructions

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 2406.17744 v1 pith:QTXJ4YD2 submitted 2024-06-25 cs.CL

Following Length Constraints in Instructions

classification cs.CL
keywords modelslengthfollowingbiasconstraintsinstructioninstructionsalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Aligned instruction following models can better fulfill user requests than their unaligned counterparts. However, it has been shown that there is a length bias in evaluation of such models, and that training algorithms tend to exploit this bias by learning longer responses. In this work we show how to train models that can be controlled at inference time with instructions containing desired length constraints. Such models are superior in length instructed evaluations, outperforming standard instruction following models such as GPT4, Llama 3 and Mixtral.

discussion (0)

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

Forward citations

Cited by 9 Pith papers

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

  1. DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination

    cs.LG 2026-06 unverdicted novelty 7.0

    DICE formalizes multi-agent LLM coordination as discounted incomplete-information Markov games and introduces Heterogeneous Quantal Response Equilibrium (HQRE) to achieve unique stable equilibria with bounded regret, ...

  2. L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

    cs.CL 2025-03 unverdicted novelty 7.0

    LCPO trains L1 reasoning models to adhere to prompt-specified CoT lengths, supporting accuracy-compute trade-offs and yielding short reasoning models that outperform larger baselines at matched lengths.

  3. DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination

    cs.LG 2026-06 conditional novelty 6.5

    HQRE entropy regularization makes multi-agent LLM coordination well-posed, yielding unique equilibria, linear mirror convergence, bounded Bayesian regret, and DICE gains of 4.3–8.5 pp on reasoning/planning tasks.

  4. Test-Time Scaling via Error Localization

    cs.LG 2026-07 conditional novelty 6.0

    TTEL uses feedback-induced token probability drops to localize the first error in a failed reasoning trace and branch a new generation from that prefix, improving pass@k per token on coding and math benchmarks.

  5. Revisiting the Reliability of Language Models in Instruction-Following

    cs.SE 2025-12 conditional novelty 6.0

    LLMs exhibit up to 61.8% performance drops on nuanced rephrasings of instruction-following tasks, revealing insufficient nuance-oriented reliability across 46 tested models.

  6. SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

    cs.CV 2026-06 unverdicted novelty 5.0

    SingGuard presents a policy-adaptive multimodal LLM guardrail family with hybrid reasoning regimes and a new benchmark of 56,340 examples, claiming SOTA F1 across 35 datasets and improved policy adherence under runtim...

  7. SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

    cs.CV 2026-06 unverdicted novelty 5.0

    SingGuard introduces a policy-adaptive multimodal LLM guardrail with dynamic reasoning regimes and SingGuard-Bench, reporting SOTA F1 scores across 35 datasets and improved policy-following accuracy under runtime shifts.

  8. Boundary Suppression Asymmetry in Post-trained Assistants: Over-expansion as a Controllability Cost

    cs.CL 2026-05 unverdicted novelty 5.0

    Post-training for helpfulness in language-model assistants produces boundary-suppression asymmetry, with over-expansion behaviors harder to locally suppress than other dimensions.

  9. Revisiting the Reliability of Language Models in Instruction-Following

    cs.SE 2025-12 conditional novelty 5.0

    Current LLMs pass single IFEval prompts but often fail to solve all cousin-prompt variants, with reliable@10 dropping up to 61.8% relative to accuracy.