TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation

• URL: http://arxiv.org/abs/2410.03608v1
• Date: Fri, 4 Oct 2024 17:09:08 GMT
• Title: TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation
• Authors: Jonathan Cook, Tim Rocktäschel, Jakob Foerster, Dennis Aumiller, Alex Wang,
• Abstract summary: TICK (Targeted Instruct-evaluation with ChecKlists) is a fully automated, interpretable evaluation protocol. We first show that, given an instruction, LLMs can reliably produce high-quality, tailored evaluation checklists. We then show that STICK can be used to improve generation quality across multiple benchmarks via self-refinement and Best-of-N selection.
• Score: 24.954629877691623
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Given the widespread adoption and usage of Large Language Models (LLMs), it is crucial to have flexible and interpretable evaluations of their instruction-following ability. Preference judgments between model outputs have become the de facto evaluation standard, despite distilling complex, multi-faceted preferences into a single ranking. Furthermore, as human annotation is slow and costly, LLMs are increasingly used to make these judgments, at the expense of reliability and interpretability. In this work, we propose TICK (Targeted Instruct-evaluation with ChecKlists), a fully automated, interpretable evaluation protocol that structures evaluations with LLM-generated, instruction-specific checklists. We first show that, given an instruction, LLMs can reliably produce high-quality, tailored evaluation checklists that decompose the instruction into a series of YES/NO questions. Each question asks whether a candidate response meets a specific requirement of the instruction. We demonstrate that using TICK leads to a significant increase (46.4% $\to$ 52.2%) in the frequency of exact agreements between LLM judgements and human preferences, as compared to having an LLM directly score an output. We then show that STICK (Self-TICK) can be used to improve generation quality across multiple benchmarks via self-refinement and Best-of-N selection. STICK self-refinement on LiveBench reasoning tasks leads to an absolute gain of $+$7.8%, whilst Best-of-N selection with STICK attains $+$6.3% absolute improvement on the real-world instruction dataset, WildBench. In light of this, structured, multi-faceted self-improvement is shown to be a promising way to further advance LLM capabilities. Finally, by providing LLM-generated checklists to human evaluators tasked with directly scoring LLM responses to WildBench instructions, we notably increase inter-annotator agreement (0.194 $\to$ 0.256).

Related papers

• $\forall$uto$\exists$$\lor\!\land$L: Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks [20.072783454089098]
  $forall$uto$exists$$lor!land$L is a novel benchmark for scaling Large Language Model (LLM) assessment in formal tasks with clear notions of correctness.
  arXiv  Detail & Related papers  (2024-10-11T00:56:37Z)
• LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints [86.59857711385833]
  We introduce RealInstruct, the first benchmark designed to evaluate LLMs' ability to follow real-world multi-constrained instructions. To address the performance gap between open-source and proprietary models, we propose the Decompose, Critique and Refine (DeCRIM) self-correction pipeline. Our results show that DeCRIM improves Mistral's performance by 7.3% on RealInstruct and 8.0% on IFEval even with weak feedback.
  arXiv  Detail & Related papers  (2024-10-09T01:25:10Z)
• PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion [96.47420221442397]
  We construct adversarial user instructions by attacking user instructions at sentence, semantic, and multi-language levels. We test 3 closed-source and 4 open-source LLMs using a benchmark that incorporates robustness settings. We find that GPT-4 exhibits the highest performance and strong robustness in our benchmark.
  arXiv  Detail & Related papers  (2024-03-06T15:33:32Z)
• PiCO: Peer Review in LLMs based on the Consistency Optimization [19.130941716491716]
  We use peer-review mechanisms to measure large language models (LLMs) automatically. We formalize it as a constrained optimization problem, intending to maximize the consistency of each LLM's capabilities and scores. We propose three metrics called PEN, CIN, and LIS to evaluate the gap in aligning human rankings.
  arXiv  Detail & Related papers  (2024-02-02T18:49:26Z)
• PRE: A Peer Review Based Large Language Model Evaluator [14.585292530642603]
  Existing paradigms rely on either human annotators or model-based evaluators to evaluate the performance of LLMs. We propose a novel framework that can automatically evaluate LLMs through a peer-review process.
  arXiv  Detail & Related papers  (2024-01-28T12:33:14Z)
• State of What Art? A Call for Multi-Prompt LLM Evaluation [28.307860675006545]
  We comprehensively analyze the brittleness of results obtained via single-prompt evaluations across 6.5M instances. To improve robustness of the analysis, we propose to evaluate LLMs with a set of diverse prompts instead.
  arXiv  Detail & Related papers  (2023-12-31T22:21:36Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization [132.25202059478065]
  We benchmark large language models (LLMs) on instruction controllable text summarization. Our study reveals that instruction controllable text summarization remains a challenging task for LLMs.
  arXiv  Detail & Related papers  (2023-11-15T18:25:26Z)
• Assessing the Reliability of Large Language Model Knowledge [78.38870272050106]
  Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. How do we evaluate the capabilities of LLMs to consistently produce factually correct answers? We propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability.
  arXiv  Detail & Related papers  (2023-10-15T12:40:30Z)
• Evaluating Large Language Models at Evaluating Instruction Following [54.49567482594617]
  We introduce a challenging meta-evaluation benchmark, LLMBar, designed to test the ability of an LLM evaluator in discerning instruction-following outputs. We discover that different evaluators exhibit distinct performance on LLMBar and even the highest-scoring ones have substantial room for improvement.
  arXiv  Detail & Related papers  (2023-10-11T16:38:11Z)

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.