Scouts Guide To The Zombie Apocalypse

Are LLMs following the correct reasoning paths?

Bangzheng Li, Ben Zhou, Fei Wang, Xingyu Fu, Dan Roth, Muhao Chen,

▶ University of California, Davis ▶ University of Pennsylvania   ▶ University of Southern California
arXiv Code Dataset

We propose a novel probing method and benchmark called EUREQA. EUREQA is an entity-searching task where a model finds a missing entity based on described multi-hop relations with other entities. These deliberately designed multi-hop relations create deceptive semantic associations, and models must stick to the correct reasoning path instead of incorrect shortcuts to find the correct answer. Experiments show that existing LLMs cannot follow correct reasoning paths and resist the attempt of greedy shortcuts. Analyses provide further evidence that LLMs rely on semantic biases to solve the task instead of proper reasoning, questioning the validity and generalizability of current LLMs’ high performances.

scouts guide to the zombie apocalypse
LLMs make errors when correct surface-level semantic cues-entities are recursively replaced with descriptions, and the errors are likely related to token similarity. GPT-3.5-turbo is used for this example.

scouts guide to the zombie apocalypse The EUREQA dataset

Download the dataset from [Dataset]

In EUREQA, every question is constructed through an implicit reasoning chain. The chain is constructed by parsing DBPedia. Each layer comprises three components: an entity, a fact about the entity, and a relation between the entity and its counterpart from the next layer. The layers stack up to create chains with different depths of reasoning. We verbalize reasoning chains into natural sentences and anonymize the entity of each layer to create the question. Questions can be solved layer by layer and each layer is guaranteed a unique answer. EUREQA is not a knowledge game: we adopt a knowledge filtering process that ensures that most LLMs have sufficient world knowledge to answer our questions.
EUREQA comprises a total of 2,991 questions of different reasoning depths and difficulties. The entities encompass a broad spectrum of topics, effectively reducing any potential bias arising from specific entity categories. These data are great for analyzing the reasoning processes of LLMs

Image 1
Categories of entities in EUREQA
Image 2
Splits of questions in EUREQA.

Scouts Guide To The Zombie Apocalypse

: A key sequence involves a "stockpiling artillery" montage where the scouts use items found in a hardware store to create makeshift weapons.

Now you know the way. Do a good turn daily. And never, ever, let the horde corner you on the latrine run.

Every scout learns archery and marksmanship. A .22 caliber bullet to the brain stem is quieter and more effective than a 12-gauge shotgun blast that attracts the whole city.

Stay sharp, stay together, and always carry a spare pair of socks. 🧦🏕️🧟

Forget standard firearms. The scouts use what they know. We see weed-whacker polearms, nail-gun modifications, and tactical uses for badges.

The zombie apocalypse has become a staple of modern popular culture, with numerous films, TV shows, and books exploring the theme. "Scout's Guide to the Zombie Apocalypse" offers a unique take on the genre, blending elements of horror, comedy, and coming-of-age drama. This report will examine the film's portrayal of the zombie apocalypse, its impact on the characters, and the themes that emerge from the narrative.

Ben (Tye Sheridan), Carter (Logan Miller), and Augie (Joey Morgan) bring a believable friendship to the screen, balancing fear with youthful enthusiasm.

From cheerleader zombies to an iconic climax in a crowded club, the film keeps the pacing fast and the humor high. 3. Characters and Performances

Never stab a zombie in the skull. The skull is curved; the knife will deflect or get stuck. Use a "hammer fist" blunt object to the temple or base of the skull.

scouts guide to the zombie apocalypse Analyses and discussion

: A key sequence involves a "stockpiling artillery" montage where the scouts use items found in a hardware store to create makeshift weapons.

Now you know the way. Do a good turn daily. And never, ever, let the horde corner you on the latrine run.

Every scout learns archery and marksmanship. A .22 caliber bullet to the brain stem is quieter and more effective than a 12-gauge shotgun blast that attracts the whole city. scouts guide to the zombie apocalypse

Stay sharp, stay together, and always carry a spare pair of socks. 🧦🏕️🧟

Forget standard firearms. The scouts use what they know. We see weed-whacker polearms, nail-gun modifications, and tactical uses for badges. : A key sequence involves a "stockpiling artillery"

The zombie apocalypse has become a staple of modern popular culture, with numerous films, TV shows, and books exploring the theme. "Scout's Guide to the Zombie Apocalypse" offers a unique take on the genre, blending elements of horror, comedy, and coming-of-age drama. This report will examine the film's portrayal of the zombie apocalypse, its impact on the characters, and the themes that emerge from the narrative.

Ben (Tye Sheridan), Carter (Logan Miller), and Augie (Joey Morgan) bring a believable friendship to the screen, balancing fear with youthful enthusiasm. And never, ever, let the horde corner you on the latrine run

From cheerleader zombies to an iconic climax in a crowded club, the film keeps the pacing fast and the humor high. 3. Characters and Performances

Never stab a zombie in the skull. The skull is curved; the knife will deflect or get stuck. Use a "hammer fist" blunt object to the temple or base of the skull.

Acknowledgement

This website is adapted from Nerfies, UniversalNER and LLaVA, licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. We thank the LLaMA team for giving us access to their models.

Usage and License Notices: The data abd code is intended and licensed for research use only. They are also restricted to uses that follow the license agreement of LLaMA, ChatGPT, and the original dataset used in the benchmark. The dataset is CC BY NC 4.0 (allowing only non-commercial use) and models trained using the dataset should not be used outside of research purposes.