Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models

• URL: http://arxiv.org/abs/2402.14848v2
• Date: Wed, 10 Jul 2024 17:01:37 GMT
• Title: Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models
• Authors: Mosh Levy, Alon Jacoby, Yoav Goldberg,
• Abstract summary: This paper explores the impact of extending input lengths on the capabilities of Large Language Models (LLMs) We isolate the effect of input length using multiple versions of the same sample, each being extended with padding of different lengths, types and locations. We show that the degradation trend appears in every version of our dataset, although at different intensities.
• Score: 48.35385912526338
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper explores the impact of extending input lengths on the capabilities of Large Language Models (LLMs). Despite LLMs advancements in recent times, their performance consistency across different input lengths is not well understood. We investigate this aspect by introducing a novel QA reasoning framework, specifically designed to assess the impact of input length. We isolate the effect of input length using multiple versions of the same sample, each being extended with padding of different lengths, types and locations. Our findings show a notable degradation in LLMs' reasoning performance at much shorter input lengths than their technical maximum. We show that the degradation trend appears in every version of our dataset, although at different intensities. Additionally, our study reveals that the traditional metric of next word prediction correlates negatively with performance of LLMs' on our reasoning dataset. We analyse our results and identify failure modes that can serve as useful guides for future research, potentially informing strategies to address the limitations observed in LLMs.

Related papers

• Evaluating Large Language Models in Vulnerability Detection Under Variable Context Windows [17.088307683654577]
  This study examines the impact of tokenized Java code length on the accuracy and explicitness of ten major LLMs in vulnerability detection. We found inconsistencies across models: some, like GPT-4, Mistral, and Mixtral, showed robustness, while others exhibited a significant link between tokenized length and performance.
  arXiv  Detail & Related papers  (2025-01-30T20:44:46Z)
• DENIAHL: In-Context Features Influence LLM Needle-In-A-Haystack Abilities [2.541099732820352]
  This study expands on previous NIAH studies by ablating NIAH features beyond typical context length. We find stark differences between GPT-3.5 and LLaMA 2-7B's performance on DENIAHL, and drops in recall performance when features like item size are increased.
  arXiv  Detail & Related papers  (2024-11-28T20:14:47Z)
• What is Wrong with Perplexity for Long-context Language Modeling? [71.34933096461124]
  Long-context inputs are crucial for large language models (LLMs) in tasks such as extended conversations, document summarization, and many-shot in-context learning. Perplexity (PPL) has proven unreliable for assessing long-context capabilities. We propose bfLongPPL, a novel metric that focuses on key tokens by employing a long-short context contrastive method to identify them.
  arXiv  Detail & Related papers  (2024-10-31T09:39:28Z)
• Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models [62.698520962933195]
  Large Vision-Language Models (LVLMs) excel in cross-model tasks but experience performance declines in long-context reasoning. We propose a novel training-free context pruning method that selectively removes less critical textual information.
  arXiv  Detail & Related papers  (2024-10-25T17:59:09Z)
• Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models [59.970391602080205]
  This study investigates whether such constraints on generation space impact LLMs abilities, including reasoning and domain knowledge comprehension. We evaluate LLMs performance when restricted to adhere to structured formats versus generating free-form responses across various common tasks. We find that stricter format constraints generally lead to greater performance degradation in reasoning tasks.
  arXiv  Detail & Related papers  (2024-08-05T13:08:24Z)
• Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost [4.5650448738679605]
  Large language models (LLMs) can solve challenging question-answering tasks. prompt engineering techniques, such as chain-of-thought (CoT), have gained attention for enhancing the explanation and correctness of outputs.
  arXiv  Detail & Related papers  (2024-07-29T09:21:52Z)
• Adapting Large Language Models for Document-Level Machine Translation [46.370862171452444]
  Large language models (LLMs) have significantly advanced various natural language processing (NLP) tasks. Recent research indicates that moderately-sized LLMs often outperform larger ones after task-specific fine-tuning. This study focuses on adapting LLMs for document-level machine translation (DocMT) for specific language pairs.
  arXiv  Detail & Related papers  (2024-01-12T09:29:13Z)
• MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Models [17.322480769274062]
  Large language models (LLMs) have shown nearly saturated performance on many natural language processing (NLP) tasks. This paper constructs Multiple Sensitive Factors Time QA (MenatQA) with total 2,853 samples for evaluating the time comprehension and reasoning abilities of LLMs.
  arXiv  Detail & Related papers  (2023-10-08T13:19:52Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)
• To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis [50.31589712761807]
  Large language models (LLMs) are notoriously token-hungry during pre-training, and high-quality text data on the web is approaching its scaling limit for LLMs. We investigate the consequences of repeating pre-training data, revealing that the model is susceptible to overfitting. Second, we examine the key factors contributing to multi-epoch degradation, finding that significant factors include dataset size, model parameters, and training objectives.
  arXiv  Detail & Related papers  (2023-05-22T17:02:15Z)

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.