paper-with-me

Papers

Large Language Models Can Be Easily Distracted by Irrelevant Context

2023-01-31 · Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed Chi, Nathanael Schärli, Denny Zhou

Large language models have achieved impressive performance on various natural language processing tasks. However, so far they have been evaluated primarily on benchmarks where all information in the input context is relevant for solving the task. In this work, we investigate the distractibility of large language models, i.e., how the model problem-solving accuracy can be influenced by irrelevant context. In particular, we introduce Grade-School Math with Irrelevant Context (GSM-IC), an arithmetic reasoning dataset with irrelevant information in the problem description. We use this benchmark to measure the distractibility of cutting-edge prompting techniques for large language models, and find that the model performance is dramatically decreased when irrelevant information is included. We also identify several approaches for mitigating this deficiency, such as decoding with self-consistency and adding to the prompt an instruction that tells the language model to ignore the irrelevant information.

📄 PDF Abstract BibTeX arXiv:2302.00093

Code (1)

google-research-datasets/gsm-ic 공식 구현

Tasks

Arithmetic ReasoningLanguage ModelingLanguage ModellingMath

Similar Papers 제목 키워드 기반

How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?

2024-04-04 · Siye Wu, Jian Xie, Jiangjie Chen, Tinghui Zhu 외

By leveraging the retrieval of information from external knowledge databases, Large Language Models (LLMs) exhibit enhanced capabilities for accomplishing many knowledge-intensive tasks. However, due to the inherent flaw…

Retrieval

Losing Visual Needles in Image Haystacks: Vision Language Models are Easily Distracted in Short and Long Contexts

2024-06-24 · Aditya Sharma, Michael Saxon, William Yang Wang

We present LoCoVQA, a dynamic benchmark generator for evaluating long-context extractive reasoning in vision language models (VLMs). LoCoVQA augments test examples for mathematical reasoning, VQA, and character recogniti…

Mathematical ReasoningVisual Question Answering (VQA)

How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark

2025-05-24 · Minglai Yang, Ethan Huang, Liang Zhang, Mihai Surdeanu 외

We introduce Grade School Math with Distracting Context (GSM-DC), a synthetic benchmark to evaluate Large Language Models' (LLMs) reasoning robustness against systematically controlled irrelevant context (IC). GSM-DC con…

Math

Differential Transformer

2024-10-07 · Tianzhu Ye, Li Dong, Yuqing Xia, Yutao Sun 외

Transformer tends to overallocate attention to irrelevant context. In this work, we introduce Diff Transformer, which amplifies attention to the relevant context while canceling noise. Specifically, the differential atte…

HallucinationIn-Context LearningInformation RetrievalLanguage Modeling+3

Medical large language models are easily distracted

2025-04-01 · Krithik Vishwanath, Anton Alyakin, Daniel Alexander Alber, Jin Vivian Lee 외

Large language models (LLMs) have the potential to transform medicine, but real-world clinical scenarios contain extraneous information that can hinder performance. The rise of assistive technologies like ambient dictati…

RAGRetrieval-augmented Generation