paper-with-me

Papers

Where is the answer? Investigating Positional Bias in Language Model Knowledge Extraction

2024-02-16 · Kuniaki Saito, Kihyuk Sohn, Chen-Yu Lee, Yoshitaka Ushiku

Large language models require updates to remain up-to-date or adapt to new domains by fine-tuning them with new documents. One key is memorizing the latest information in a way that the memorized information is extractable with a query prompt. However, LLMs suffer from a phenomenon called perplexity curse; despite minimizing document perplexity during fine-tuning, LLMs struggle to extract information through a prompt sentence. In this new knowledge acquisition and extraction, we find a very intriguing fact that LLMs can accurately answer questions about the first sentence, but they struggle to extract information described in the middle or end of the documents used for fine-tuning. Our study suggests that the auto-regressive training causes this issue; each token is prompted by reliance on all previous tokens, which hinders the model from recalling information from training documents by question prompts. To conduct the in-depth study, we publish both synthetic and real datasets, enabling the evaluation of the QA performance w.r.t. the position of the corresponding answer in a document. Our investigation shows that even a large model suffers from the perplexity curse, but regularization such as denoising auto-regressive loss can enhance the information extraction from diverse positions. These findings will be (i) a key to improving knowledge extraction from LLMs and (ii) new elements to discuss the trade-off between RAG and fine-tuning in adapting LLMs to a new domain.

📄 PDF Abstract BibTeX arXiv:2402.12170

Code (1)

omron-sinicx/whereistheanswer 공식 구현 pytorch

Tasks

DenoisingLanguage ModelingLanguage ModellingQuestion AnsweringRAGSentence

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
WordPiece 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

On Evaluating Multilingual Compositional Generalization with Translated Datasets

2023-06-20 · Zi Wang, Daniel Hershcovich

Compositional generalization allows efficient learning and human-like inductive biases. Since most research investigating compositional generalization in NLP is done on English, important questions remain underexplored. …

Machine TranslationSemantic ParsingTranslation

Do Large Language Models Plan Answer Positions? Position Bias in Multiple-Choice Question Generation

2026-05-03 · Xuemei Tang, Xufeng Duan, Zhenguang G. Cai arxiv

Large language models (LLMs) are increasingly used to generate multiple-choice questions (MCQs), where correct answers should ideally be uniformly distributed across options. However, we observe that LLMs exhibit systema…

Question Generation

Verbosity Bias in Preference Labeling by Large Language Models

2023-10-16 · Keita Saito, Akifumi Wachi, Koki Wataoka, Youhei Akimoto

In recent years, Large Language Models (LLMs) have witnessed a remarkable surge in prevalence, altering the landscape of natural language processing and machine learning. One key factor in improving the performance of LL…

reinforcement-learningReinforcement Learning

A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks

2025-06-09 · Vishaal Udandarao, Mehdi Cherti, Shyamgopal Karthik, Jenia Jitsev 외

We investigate 17 benchmarks (e.g. SugarCREPE, VALSE) commonly used for measuring compositional understanding capabilities of vision-language models (VLMs). We scrutinize design choices in their construction, including d…

Language ModelingLanguage Modelling

Exploiting Primacy Effect To Improve Large Language Models

2025-07-18 · Bianca Raimondi, Maurizio Gabbrielli arxiv

Large Language Models (LLMs) have become essential in many Natural Language Processing (NLP) tasks, leveraging extensive pre-training and fine-tuning to achieve high accuracy. However, like humans, LLMs exhibit biases, p…

Semantic SimilarityQuestion Answering