LLM Output Detectability and Task Performance Can be Jointly Optimized

• URL: http://arxiv.org/abs/2605.01350v1
• Date: Sat, 02 May 2026 09:50:51 GMT
• Title: LLM Output Detectability and Task Performance Can be Jointly Optimized
• Abstract summary: PUPPET is a framework that fine-tunes large language models to generate text that is both more detectable and better performing on downstream tasks.<n>Experiments on long-form QA, summarization, and essay writing show that LLMs trained with PUPPET achieve high detectability competitive with watermarking methods.
• Score: 29.75569649982415
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Detecting machine-generated text is essential for transparency and accountability when deploying large language models (LLMs). Among detection approaches, watermarking is a statistically reliable method by design -- it embeds detectable signals into LLM outputs by biasing their token distributions. However, it has been reported that watermarked LLMs often perform worse on downstream tasks. We propose PUPPET, a framework that fine-tunes an LLM via reinforcement learning to generate text that is both more detectable and better performing on downstream tasks. We use two reward functions: a detector that outputs a machine-class likelihood and an evaluator that measures a task-specific metric. Experiments on long-form QA, summarization, and essay writing show that LLMs trained with PUPPET achieve high detectability competitive with watermarking methods while outperforming them on downstream tasks. The analysis shows that this optimization can be performed efficiently with only a few thousand samples in 1--2 GPU hours. Moreover, these gains are consistent across out-of-domain tasks, different LLM families, and model sizes, and are even robust to paraphrasing attacks.

Related papers

• LLM Detection as an Intervention: Downstream Impact under Strategic User Behavior [53.63441578662801]
  Detectors operate as an intervention that steers not only the detected attribute itself, but also downstream metrics such as LLM usage and output quality.<n>We develop a stylized model which captures how users strategically choose how much to use the LLM and how to post-process content to reduce the detected attribute.<n>We find that even when reducing the detected attribute improves output quality, introducing an LLM detector can lead users to produce lower quality outputs.
  arXiv  Detail & Related papers  (2026-07-21T17:11:02Z)
• DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection [39.153744982595036]
  We propose Detection Prompt Optimization (DetPO), a gradient-free test-time optimization approach.<n>Our proposed approach yields consistent improvements across generalist MLLMs on Roboflow20-VL and LVIS.
  arXiv  Detail & Related papers  (2026-03-24T17:26:55Z)
• DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models [60.713908578319256]
  We propose Direct Discrepancy Learning (DDL) to optimize the detector with task-oriented knowledge.<n>Built upon this, we introduce DetectAnyLLM, a unified detection framework that achieves state-of-the-art MGTD performance.<n>MIRAGE samples human-written texts from 10 corpora across 5 text-domains, which are then re-generated or revised using 17 cutting-edge LLMs.
  arXiv  Detail & Related papers  (2025-09-15T10:59:57Z)
• On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization [54.965787768076254]
  Large Language Models have been recently exploited as judges for complex natural language processing tasks, such as Q&A.<n>We study the effectiveness of LLMs-as-a-judge for two code-related tasks, namely code generation and code summarization.
  arXiv  Detail & Related papers  (2025-07-22T13:40:26Z)
• Watermarking LLM-Generated Datasets in Downstream Tasks [26.31171813997747]
  Large Language Models (LLMs) have experienced rapid advancements, with applications spanning a wide range of fields, including sentiment classification, review generation, and question answering.<n>Due to their efficiency and versatility, researchers and companies increasingly employ LLM-generated data to train their models.<n>The inability to track content produced by LLMs poses a significant challenge, potentially leading to copyright infringement for the LLM owners.<n>We propose a method for injecting watermarks into LLM-generated datasets, enabling the tracking of downstream tasks to detect whether these datasets were produced using the original LLM.
  arXiv  Detail & Related papers  (2025-06-16T13:51:49Z)
• Get my drift? Catching LLM Task Drift with Activation Deltas [55.75645403965326]
  Task drift allows attackers to exfiltrate data or influence the LLM's output for other users.<n>We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set.<n>We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
  arXiv  Detail & Related papers  (2024-06-02T16:53:21Z)
• Take One Step at a Time to Know Incremental Utility of Demonstration: An Analysis on Reranking for Few-Shot In-Context Learning [23.932500424117244]
  In-Context Learning (ICL) is an emergent capability of Large Language Models (LLMs) Previous studies have shown that using LLMs' outputs as labels is effective in training models to select demonstrations. This paper presents an analysis on different utility functions by focusing on LLMs' output probability given ground-truth output.
  arXiv  Detail & Related papers  (2023-11-16T07:03:54Z)
• TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models [52.734140807634624]
  Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. Existing continual learning benchmarks lack sufficient challenge for leading aligned LLMs. We introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
  arXiv  Detail & Related papers  (2023-10-10T16:38:49Z)
• LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
  Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset. Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
  arXiv  Detail & Related papers  (2023-05-19T12:10:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.