paper-with-me

홈 › Papers

DENIAHL: In-Context Features Influence LLM Needle-In-A-Haystack Abilities

2024-11-28 · Hui Dai, Dan Pechi, Xinyi Yang, Garvit Banga, Raghav Mantri

The Needle-in-a-haystack (NIAH) test is a general task used to assess language models' (LMs') abilities to recall particular information from long input context. This framework however does not provide a means of analyzing what factors, beyond context length, contribute to LMs' abilities or inabilities to separate and recall needles from their haystacks. To provide a systematic means of assessing what features contribute to LMs' NIAH capabilities, we developed a synthetic benchmark called DENIAHL (Data-oriented Evaluation of NIAH for LLM's). Our work expands on previous NIAH studies by ablating NIAH features beyond typical context length including data type, size, and patterns. 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, and to some degree when data type is changed from numbers to letters. This has implications for increasingly large context models, demonstrating factors beyond item-number impact NIAH capabilities.

📄 PDF Abstract BibTeX arXiv:2411.19360

Code (1)

ameliadai/DENIAHL 공식 구현

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Multi-Head Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Weight Decay 설명 없음
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
Residual Connection 설명 없음
Attention 설명 없음

Similar Papers 제목 키워드 기반

Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models

2024-06-17 · Hengyi Wang, Haizhou Shi, Shiwei Tan, Weiyi Qin 외

Multimodal Large Language Models (MLLMs) have shown significant promise in various applications, leading to broad interest from researchers and practitioners alike. However, a comprehensive evaluation of their long-conte…

BenchmarkingHallucinationImage Retrieval+4

LLM In-Context Recall is Prompt Dependent

2024-04-13 · Daniel Machlab, Rick Battle

The proliferation of Large Language Models (LLMs) highlights the critical importance of conducting thorough evaluations to discern their comparative advantages, limitations, and optimal use cases. Particularly important …

NoLiMa: Long-Context Evaluation Beyond Literal Matching

2025-02-07 · Ali Modarressi, Hanieh Deilamsalehy, Franck Dernoncourt, Trung Bui 외

Recent large language models (LLMs) support long contexts ranging from 128K to 1M tokens. A popular method for evaluating these capabilities is the needle-in-a-haystack (NIAH) test, which involves retrieving a "needle" (…

Multilingual Needle in a Haystack: Investigating Long-Context Behavior of Multilingual Large Language Models

2024-08-19 · Amey Hengle, Prasoon Bajpai, Soham Dan, Tanmoy Chakraborty

While recent large language models (LLMs) demonstrate remarkable abilities in responding to queries in diverse languages, their ability to handle long multilingual contexts is unexplored. As such, a systematic evaluation…

8kInformation RetrievalQuestion AnsweringRetrieval

GOLD PANNING: Strategic Context Shuffling for Needle-in-Haystack Reasoning

2025-10-10 · Adam Byerly, Daniel Khashabi arxiv

Large language models (LLMs) exhibit pronounced position bias in long-context needle-in-haystack problems, systematically prioritizing the location of information over its relevance. While current mitigations rely on whi…

Active Learning