# LLMs Remember First, Forget Last: Dual-Process Interference in Large Language Models

arXiv: https://arxiv.org/abs/2603.00270 · HTML: https://mlsanity.com/paper/2603.00270/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [NoLiMa: Long-Context Evaluation Beyond Literal Matching](https://mlsanity.com/paper/2502.05167/) (2025)
- [Polysemanticity and Capacity in Neural Networks](https://mlsanity.com/paper/2210.01892/) (2022)
- [LongReason: A Synthetic Long-Context Reasoning Benchmark via Context Expansion](https://mlsanity.com/paper/2501.15089/) (2025)
- [Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length](https://mlsanity.com/paper/2506.08184/) (2025)
- [AbsenceBench: Language Models Can't Tell What's Missing](https://mlsanity.com/paper/2506.11440/) (2025)

## Built on by (most cited first, 1 of 1)

- [When Context Changes: Understanding Update Failures in LLMs](https://mlsanity.com/paper/2609.38866/) (2026)

## Abstract (arXiv)

Large language models can process millions of tokens, yet how they handle conflicting information within context remains poorly understood. From patient health logs tracking evolving vital signs to legal documents with superseding clauses, real-world applications routinely require models to retrieve specific values from streams of semantically similar, competing updates. We adapt classical interference paradigms from cognitive psychology to compare retroactive interference (RI; recalling initial values after updates) and proactive interference (PI; recalling recent values despite competing prior encodings) across 39 LLMs spanning 1B to 2.5T parameters. Every model exhibits the same pattern: PI causes substantially greater degradation than RI (d = 1.73), the opposite of the typical human finding where new information more readily disrupts old. Four lines of evidence indicate that RI and PI engage distinct mechanisms: model size predicts RI resistance but not PI; the two scores correlate only weakly; error analysis reveals qualitatively different failure profiles, with RI failures reflecting passive retrieval failure and PI failures reflecting active primacy intrusion; and hallucination rates remain below 1% in both conditions. An adaptive bootstrap design further shows that RI decays smoothly while PI collapses bimodally at high interference, consistent with gradual dilution versus winner-take-all attention dynamics. These findings characterize a systematic primacy bias in transformer attention, with implications for reliable deployment in settings where in-context information evolves over time.