[HN Gopher] Thought Propagation: An analogical approach to compl...
___________________________________________________________________
Thought Propagation: An analogical approach to complex reasoning
with LLMs
Author : amilios
Score : 36 points
Date : 2023-10-10 19:55 UTC (3 hours ago)
(HTM) web link (paperswithcode.com)
(TXT) w3m dump (paperswithcode.com)
| amilios wrote:
| Abstract: Large Language Models (LLMs) have achieved remarkable
| success in reasoning tasks with the development of prompting
| methods. However, existing prompting approaches cannot reuse
| insights of solving similar problems and suffer from accumulated
| errors in multi-step reasoning, since they prompt LLMs to reason
| _from scratch_. To address these issues, we propose _Thought
| Propagation_ (TP), which explores the analogous problems and
| leverages their solutions to enhance the complex reasoning
| ability of LLMs. These analogous problems are related to the
| input one, with reusable solutions and problem-solving
| strategies. Thus, it is promising to propagate insights of
| solving previous analogous problems to inspire new problem-
| solving. To achieve this, TP first prompts LLMs to propose and
| solve a set of analogous problems that are related to the input
| one. Then, TP reuses the results of analogous problems to
| directly yield a new solution or derive a knowledge-intensive
| plan for execution to amend the initial solution obtained from
| scratch. TP is compatible with existing prompting approaches,
| allowing plug-and-play generalization and enhancement in a wide
| range of tasks without much labor in task-specific prompt
| engineering. Experiments across three challenging tasks
| demonstrate TP enjoys a substantial improvement over the
| baselines by an average of 12% absolute increase in finding the
| optimal solutions in Shortest-path Reasoning, 13% improvement of
| human preference in Creative Writing, and 15% enhancement in the
| task completion rate of LLM-Agent Planning.
| mjhay wrote:
| Solving a set of analogous problems and then refining from those
| doesn't sound all that different from the general idea of adding
| another layer.
| bpiche wrote:
| Seems like chain of thought.. except instead of giving the llm an
| explicit set of instructions and having the llm step through a
| series of problems, you give it a simple instruction and it
| hallucinates an analogous series of steps that are statistically
| relevant.
|
| Could be interesting. Some of the best innovations in human
| history were basically highdeas cooked up in the shower by
| associating a hard problem with something else.
|
| Are you the same user who got some flak for posting the abstract
| of a paper without quotations recently? Keep on truckin'.
| amilios wrote:
| The abstract of a paper without quotations? No, I don't think
| so. What do you mean exactly? Someone posted the abstract as a
| text post directly?
| bpiche wrote:
| I was mistaken, it was not you, but it did happen recently.
| My apologies.
|
| https://news.ycombinator.com/item?id=37816614
| amilios wrote:
| Ah I see. Yeah the criticism seems fair, gotta at least
| prepend "Abstract:" or something haha.
| swatcoder wrote:
| Even with the prefix, it's not really HN etiquette to
| post comments that are entirely or predominantly pasted.
| And I'm happy about that.
|
| Even here, you're "Abstract:" comment was just a wall of
| text that would have been easier to read on the other end
| of that URL and with little less convenience. There's
| just no need for it to be pasted in as a comment as well,
| unless you had something substantial to add alongside it.
| Philpax wrote:
| I wouldn't generalise your preferences to HN etiquette.
|
| I personally like having some context in the comments as
| I often check the comments before the link - that allows
| me to see what the community thinks of the content before
| I check it out for myself.
| swatcoder wrote:
| I'm with you in reading comments first, but I look for
| _comments_ there, not uncommented pastes.
___________________________________________________________________
(page generated 2023-10-10 23:01 UTC)