BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack
read the original abstract
In recent years, the input context sizes of large language models (LLMs) have increased dramatically. However, existing evaluation methods have not kept pace, failing to comprehensively assess the efficiency of models in handling long contexts. To bridge this gap, we introduce the BABILong benchmark, designed to test language models' ability to reason across facts distributed in extremely long documents. BABILong includes a diverse set of 20 reasoning tasks, including fact chaining, simple induction, deduction, counting, and handling lists/sets. These tasks are challenging on their own, and even more demanding when the required facts are scattered across long natural text. Our evaluations show that popular LLMs effectively utilize only 10-20\% of the context and their performance declines sharply with increased reasoning complexity. Among alternatives to in-context reasoning, Retrieval-Augmented Generation methods achieve a modest 60\% accuracy on single-fact question answering, independent of context length. Among context extension methods, the highest performance is demonstrated by recurrent memory transformers after fine-tuning, enabling the processing of lengths up to 50 million tokens. The BABILong benchmark is extendable to any length to support the evaluation of new upcoming models with increased capabilities, and we provide splits up to 10 million token lengths.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
RULER: What's the Real Context Size of Your Long-Context Language Models?
RULER shows most long-context LMs drop sharply in performance on complex tasks as length and difficulty increase, with only half maintaining results at 32K tokens.
-
Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks
Audits reveal no reasoning benchmark controls position/filler/length jointly; CRE shows LLMs drop up to 88pp on middle-position tasks at 64K context, with diagnostic probe supporting positional cause.
-
BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections
BridgeEQA creates a new benchmark and EMVR method for embodied agents to perform question answering on real-world bridge inspections using egocentric images and professional reports.
-
Diagnosing Evidence Utilization in Long-Context and Retrieval-Augmented Language Models under Matched Evidence Conditions
Introduces a matched four-condition protocol and ONCU metric to diagnose evidence utilization in long-context and RAG models across synthetic and multi-hop QA tasks.
-
Retrieval and Multi-Hop Reasoning in 1M-Token Context Windows: Evaluating LLMs on Classical Chinese Text
Frontier LLMs solve single-needle retrieval at 1M tokens on classical Chinese but show three distinct accuracy-decay patterns in three-hop reasoning between 256K and 1M tokens.
-
Randomized YaRN Improves Length Generalization for Long-Context Reasoning
Randomized YaRN improves LLM reasoning performance on 16K-128K contexts when trained only on <8K data by randomizing YaRN positional encodings during short-context training.
-
Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces
Reasoning in large output spaces proceeds via shortlisting then fine-grained reasoning; this characterization enables a mechanistic distillation strategy that outperforms standard distillation.
-
The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes
A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.