The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" · HackerPapers discussions

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" — mentioned by tcp_handshaker

Wed, 12 Aug 2026 11:41:47 GMT

Its the tools. Sell those RSUs while they last. Most of these are 2026.... Frontier LLMs Still Struggle with Simple Reasoning Tasks - https://arxiv.org/abs/2507.07313 General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks - https://arxiv.org/abs/2604.11778 LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening - https://arxiv.org/abs/2605.19597 LogicGraph: Benchmarking Multi-Path Logical Reasoning via Neuro-Symbolic Generation and Verification - https://arxiv.org/abs/2602.21044…

Paper and discussion history. A mention is not an endorsement.

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" — mentioned by kgeist

Mon, 06 Jul 2026 22:01:49 GMT

Probably an instance of: "The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" https://arxiv.org/abs/2309.12288

Paper and discussion history. A mention is not an endorsement.

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" — HN submission

Tue, 23 Jun 2026 11:07:05 GMT

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" (2023)

25 points; 46 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" — mentioned by Gormisdomai

Wed, 12 Nov 2025 18:50:44 GMT

Related: LLMs trained on "A is B" fail to learn "B is A" https://arxiv.org/abs/2309.12288

Paper and discussion history. A mention is not an endorsement.

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" — mentioned by michaelt

Thu, 18 Jul 2024 16:50:16 GMT

I don't have explanations but I can point you to one of the papers: https://arxiv.org/pdf/2309.12288 which calls it "the reversal curse" and does a bunch of experiments showing models that are successful at questions like "Who is Tom Cruise’s mother?" (Mary Lee Pfeiffer) will not be equally successful at answering "Who is Mary Lee Pfeiffer’s son?"

Paper and discussion history. A mention is not an endorsement.

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" — mentioned by toisanji

Sat, 15 Jun 2024 21:25:58 GMT

I've written about the cognitive aspect the author talks about before: https://blog.jtoy.net/examining-concepts-through-different-f... https://blog.jtoy.net/on-the-wondrous-human-simulation-engin... https://arxiv.org/abs/2210.12068 The human brain has at least over 12 different coordinate systems. I like to reference this image: https://cln.sh/gpqhwrw2Hg92MQz62TY6 Humans have the ability to inspect anything from any point of view that we want, like a real time video game simulation system in our minds. I suspect that artificial neural networks are missing this core ability to encode and…

Paper and discussion history. A mention is not an endorsement.

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" — mentioned by williamtrask

Sat, 25 May 2024 03:51:49 GMT

Related papers: - https://arxiv.org/abs/2307.06962 - https://arxiv.org/abs/2309.12288 - https://arxiv.org/abs/2112.04426 - https://huggingface.co/papers/2405.14860

Paper and discussion history. A mention is not an endorsement.

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" — mentioned by sgt101

Mon, 22 Jan 2024 18:52:21 GMT

My take is when the model can't do the things that you would expect it to do if it were reasoning, and instead does the things that you would expect it to do if it were an approximate retrieval system with an enormous knowledge base. this is a good paper: https://arxiv.org/abs/2309.12288

Paper and discussion history. A mention is not an endorsement.

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" — mentioned by cedws

Sat, 18 Nov 2023 05:30:42 GMT

>Ilya claims the transformer architecture, with some modification for efficiency, is actually sufficient for AGI. I thought this guy was supposed to know what he's talking about? There was a paper that shows LLMs cannot generalise[0]. Anybody who's used ChatGPT can see there's imperfections. [0] https://arxiv.org/abs/2309.12288

Paper and discussion history. A mention is not an endorsement.

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" — mentioned by sandkoan

Tue, 07 Nov 2023 19:59:51 GMT

For anyone else interested, the paper he's referring to is "The Reversal Curse": https://arxiv.org/abs/2309.12288.

Paper and discussion history. A mention is not an endorsement.

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" — mentioned by famouswaffles

Mon, 09 Oct 2023 21:00:57 GMT

> Numbers (LLMs still can't do math and the ones that "can" are very brute forced and don't generalize) These seem to generalize. https://arxiv.org/abs/2211.09066 https://arxiv.org/abs/2308.00304 > Commutative properties (The (idk why anyone was surprised) "reversal curse": https://arxiv.org/abs/2309.12288) This was a retrieval from training issue not an inference one. and make no mistake, people will fail these sort of answers too (perhaps not to the same extent). Very often someone will learn a fact in a certain why and fail to recall that when asked in a reverse or roundabout way.…

Paper and discussion history. A mention is not an endorsement.

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" — mentioned by godelski

Mon, 09 Oct 2023 20:44:41 GMT

To add to this list of things LLMs don't understand: - Numbers (LLMs still can't do math and the ones that "can" are very brute forced and don't generalize) - Commutative properties (The (idk why anyone was surprised) "reversal curse": https://arxiv.org/abs/2309.12288) - Associative properties - World models (i.e. can understand some basic physics and causality. Not mathematically, but the same way a child understands that letting go of something in their hand falls to the ground and not up) - How to say "I don't know" - Any form of meaningful generalization (GPT 3.5 and most LLMs still have…

Paper and discussion history. A mention is not an endorsement.