The Reversal Curse: Why a Language Model That Knows “A Is B” Can’t Tell You “B Is A”
Large Language ModelsThe Reversal Curse: Why a Language Model That Knows “A Is B” Can’t Tell You “B Is A”A model can recall a fact in the direction it learned it and fail in the other. Here's a toy version of whyUtkarsh MangalOctober 4, 202610 min readImage by author, generated by ai.Say a friend tells you their dog’s name is Biscuit. Later, at the park, a stranger points at a dog and asks if you know whose it is.
- ▪Large Language ModelsThe Reversal Curse: Why a Language Model That Knows “A Is B” Can’t Tell You “B Is A”A model can recall a fact in the direction it learned it and fail in the other.
- ▪Here's a toy version of whyUtkarsh MangalOctober 4, 202610 min readImage by author, generated by ai.Say a friend tells you their dog’s name is Biscuit.
- ▪Later, at the park, a stranger points at a dog and asks if you know whose it is.
Towards Data Science files mainly under ai. We currently carry 209 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Towards Data Science |
| Canonical URL | https://towardsdatascience.com/the-reversal-curse-why-a-language-model-that-knows-a-is-b-cant-tell-you-b-is-a/ |
| Publication time | Sun, 04 Oct 2026 12:00:00 GMT |
| Retrieval time | 2026-10-04T12:04:07.839Z |
| Last seen | 2026-10-04T12:04:07.839Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | _btcJTEvUYRr · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Large Language ModelsThe Reversal Curse: Why a Language Model That Knows “A Is B” Can’t Tell You “B Is A”A model can recall a fact in the direction it learned it and fail in the other. Here's a toy version of whyUtkarsh MangalOctober 4, 202610 min readImage by author, generated by ai.Say a friend tells you their dog’s name is Biscuit. Later, at the park, a stranger points at a dog and asks if you know whose it is. If that dog happens to be Biscuit, you’d probably recognize it. The fact “Sam’s dog is named Biscuit” works in your head whichever direction someone approaches it from, and that flexibility feels so basic we don’t notice we’re relying on it.A 2023 paper by Berglund and colleagues [1] argues that language models don’t get this for free.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Towards Data Science.
Discussion
0 commentsMore from Towards Data Science
