Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Chain-of-Thought Reasoning in the Wild Is Not Always Faithful (2025)

arxiv.org

Post reply on HN
Print view View original

21–30 of 46 posts

Re: Chain-of-Thought Reasoning in the Wild Is Not Always Faithful (2025)

#21

Post by gopher_space »

tyg13 wrote: post #8
Georgelemental wrote: post #5

Earlier quoted context omitted.

Natural intelligences do this too

Must we always see this restated every time? It's getting a bit stale always seeing these kinds of comments on articles about LLM.

It's the grounded portion of a feedback loop searching for the 'why is this happening' thinking. I'd imagine most of my own comments in this area boil down to "GIGO" most of the time.

It's a relevant comment in this instance because we're discussing concepts you need to be both trained and practiced in to reason about, and that our discipline has traditionally been blind to. Plenty of people working with LLM context issues who've never been exposed to the idea of 'subtext' or could tell you why it would matter to their direction of effort.

Re: Chain-of-Thought Reasoning in the Wild Is Not Always Faithful (2025)

#22

Post by Planktonne »

Of course not. Because the article uses the words 'thought' and 'reasoning' and even 'faithful' to mean something other than their normal meanings, but then expects them to behave exactly the same.

Every field has terms of art, and 'reasoning' is one for LLMs. But that doesn't mean it has the same properties as 'reasoning' in other contexts, because you're not referring to the same thing.

Why doesn't my asteroid belt buckle?

Re: Chain-of-Thought Reasoning in the Wild Is Not Always Faithful (2025)

#23

Post by ethin »

Georgelemental wrote: post #5
florianherrengt wrote: post #2

This paper puts words to something I’ve noticed repeatedly with LLMs, particularly Qwen3.6. When I read its reasoning, it appears to recognise the mistake and then carry on as if it hadn’t noticed it at all. > models often determine their answers based on implicit biases tied to question templates, then construct reasoning chains to justify their predetermined conclusions > its reasoning was correct right until the f…

Natural intelligences do this too

[flagged]

Re: Chain-of-Thought Reasoning in the Wild Is Not Always Faithful (2025)

#24

Post by stymaar »

Planktonne wrote: post #22

Of course not. Because the article uses the words 'thought' and 'reasoning' and even 'faithful' to mean something other than their normal meanings, but then expects them to behave exactly the same. Every field has terms of art, and 'reasoning' is one for LLMs. But that doesn't mean it has the same properties as 'reasoning' in other contexts, because you're not referring to the same thing. Why doesn't my asteroid belt…

Related: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces![1]

> Our findings consistently challenge the prevailing narrative that intermediate tokens constitute a semantically meaningful reasoning process. First, we observe a pronounced lack of correlation between solution correctness and trace validity—models frequently produce invalid reasoning traces even when they arrive at correct solutions. Second, and more strikingly, models trained on corrupted or semantically irrelevant traces achieve performance comparable to, and often exceeding, that of models trained on correct traces, especially on out-of-distribution tasks.

[1]: https://arxiv.org/abs/2504.09762

Re: Chain-of-Thought Reasoning in the Wild Is Not Always Faithful (2025)

#25

Post by 8note »

tyg13 wrote: post #8
Georgelemental wrote: post #5

Earlier quoted context omitted.

Natural intelligences do this too

Must we always see this restated every time? It's getting a bit stale always seeing these kinds of comments on articles about LLM.

or rather, its not productive to "we should do better with artificial intelligence"

Re: Chain-of-Thought Reasoning in the Wild Is Not Always Faithful (2025)

#26

Post by ethin »

tyg13 wrote: post #8
Georgelemental wrote: post #5

Earlier quoted context omitted.

Natural intelligences do this too

Must we always see this restated every time? It's getting a bit stale always seeing these kinds of comments on articles about LLM.

I agree, and I very strongly dislike it, to be polite about it. It contributes absolutely nothing and is an excellent way of hand-waving away literally anything an AI model does. Saying "well people do this too" is a great way to rationalize away anything you can imagine that an AI model would be capable of, because "humans do it too so what's the big deal, guys?"

Re: Chain-of-Thought Reasoning in the Wild Is Not Always Faithful (2025)

#27

Post by 8note »

gopher_space wrote: post #21
tyg13 wrote: post #8

Earlier quoted context omitted.

Must we always see this restated every time? It's getting a bit stale always seeing these kinds of comments on articles about LLM.

It's the grounded portion of a feedback loop searching for the 'why is this happening' thinking. I'd imagine most of my own comments in this area boil down to "GIGO" most of the time. It's a relevant comment in this instance because we're discussing concepts you need to be both trained and practiced in to reason about, and that our discipline has traditionally been blind to. Plenty of people working with LLM context…

continuing with the "we need open training data" thread

how much of the training data had thinking traces that dont make sense to people as being actually a description of why the output should be that way?

Re: Chain-of-Thought Reasoning in the Wild Is Not Always Faithful (2025)

#28

Post by 8note »

ForHackernews wrote: post #11

I thought this was already widely known? From March last year: https://transformer-circuits.pub/2025/attribution-graphs/bio... There's no reason to believe the model's self-reported "thinking" bears any relation to the mechanics by which it arrived at some output.

that sounds testable - if you skip the reasoning tokens, do you get the same result?

if not, then there's certainly some bearing, but not necessarily in how we read the tokens as text

Re: Chain-of-Thought Reasoning in the Wild Is Not Always Faithful (2025)

#29

Post by dgellow »

delichon wrote: post #20
elictronic wrote: post #17

Earlier quoted context omitted.

The current political climate is well reasoned and intentional. It might not be yours or mine, however the system is working exactly as the ones paying for it have intended.

My brother and I have been arguing about that all of our lives. He believes everything is intentional and it's just a matter of discovering who benefits. I see chaos that nobody intends or controls. His political landscape is a tapestry of conspiracy theories and mine is a fog of war. I think his is more comforting, since it admits a possibility of a rational, predictable world.

It’s intentional in the sense that actors are acting intentionally for their own benefit (or at least what they believe is beneficial) and following incentives. Not that there is a master planner who manipulates everything

Re: Chain-of-Thought Reasoning in the Wild Is Not Always Faithful (2025)

#30

Post by sergio_valencia »

This paper made me wonder not whether the chain we can read is actual “thought,” but what conclusions we can draw by observing it. It is an output channel, but not direct access to the black box that creates it. The question pairs present an interesting experiment, but they also got me thinking about semantics: the same underlying relation can have many valid representations, and how models reason across those representations can tell us more about their stability and correctness. Basically, are models semantically consistent when given different representations of the same underlying relation? Do their answers transform as the relationship requires, and do their explanations remain consistent with that relationship?
Post reply on HN