Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks · HackerPapers discussions

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks — mentioned by dl9999

Sat, 30 Nov 2024 16:46:53 GMT

Is there something more than prediction going on? I'd like to understand why there would be studies like this: https://arxiv.org/pdf/2307.02477 if it's all just prediction. Are there some algorithms that are called "reasoning", that are somewhere between prediction and full-blown reasoning?

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

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks — mentioned by famouswaffles

Mon, 19 Aug 2024 18:36:47 GMT

>Your last linked paper has flawed methodology for what it attempts to demonstrate, as shown in this paper: https://arxiv.org/pdf/2307.02477 Genuinely, What's wrong with the methodology? Your paper literally admits humans would also perform worse at counterfactuals. Worse than a LLM ? Maybe not but it never bothers to test this so... The problem here is that none of the definitions (those that are testable) so far given actually separate humans from LLMs. They're all tests some humans would also flounder at or that LLMs perform far greater than chance at, if below some human's level. If…

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

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks — mentioned by HAL3000

Mon, 19 Aug 2024 17:17:23 GMT

It appears that you are the only person in this discussion making many incorrect assumptions. Based on your comments, I would assume you are actually googling those papers based on their abstracts. Your last linked paper has flawed methodology for what it attempts to demonstrate, as shown in this paper: https://arxiv.org/pdf/2307.02477 The tests you're requesting are provided within the previously linked papers. I'm not sure what you want. Do you expect people to copy and paste entire papers here that show methodology and describe experiments? You wrote, "I'm asking you to define 'real…

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

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks — mentioned by cowsaymoo

Mon, 15 Jul 2024 16:38:33 GMT

Same, I've been pretty impressed as well and typically give Claude a shot. Sometimes I even pass their results back and forth in an LLM collab so they generate more diverse perspectives. However, this paper from 4 days ago shows that Claude can fall apart quickly in out of distribution tasks. If you ask opposite day questions, GPT-4 is weirdly strong at it (figure 2). https://arxiv.org/pdf/2307.02477

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

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks — mentioned by mjburgess

Sat, 08 Jun 2024 16:04:44 GMT

Yes, we cannot learn anything about reality from language alone. This is 'the intentional illusion' or you could call it 'the aboutness illusion'. As in you think you are learning a speed limit for a road by looking at a sign with a speed limit on it. But the sign itself is just some shapes, and no aspect of its structure has anything to do with speed, roads, or speed limits. Literally, everything here is arbitrary convention; and under arbitrary permutation, the sign can mean the same, and share no properties with any other permutation whatsoever. Rather it is by being-in-the-world you have…

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

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks — mentioned by sgt101

Thu, 28 Dec 2023 09:11:47 GMT

I think it regurgitates badly, an interesting pre-print is the "reasoning or reciting" one from https://arxiv.org/abs/2307.02477 But - it's only a pre-print and I don't think that they have taken it forward to a publication so handle with care. Anyway, the relevant evidence and thinking that I would highlight and somewhat agrees with my findings is seen in figure 7 and section 5.6. I struggle to get the quality of results that they saw, but its believed by some people that ongoing development of GPT-4 and throttling of the reasoning for cost reasons may have limited some of its capabilities…

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

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks — HN submission

Mon, 25 Sep 2023 17:42:47 GMT

Exploring Capabilities, Limitations of Language Models by Counterfactual Tasks

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks — mentioned by skepticATX

Tue, 11 Jul 2023 15:47:30 GMT

Exactly. Current LLMs fall over when facing counterfactuals: https://arxiv.org/abs/2307.02477. This is why it's mostly meaningless to for a LLM to pass the bar, but not meaningless for a human to do so. We (rightly, for the most part) assume that a human who passes the bar can transfer those skills into unique and novel situations. We can't make that assumption for LLMs, because they are lacking adaptability that is needed for true intelligence.

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