| ▲ | rob74 4 hours ago |
| I think current LLMs would be completely lost with the task "scan these documents for information that could be risky for our case": they would either produce tons of false positives, overlook actual risks, or both. |
|
| ▲ | maeil 2 hours ago | parent | next [-] |
| I can personally attest that companies are already using those LLM-based workflows for those exact purposes successfully, performing better than humans, which often isn't a super high bar. |
|
| ▲ | mschuster91 3 hours ago | parent | prev | next [-] |
| At least you can reasonably use them for translation and in a second pass summarize or just have it detect if a document contains specific keywords / phrases. |
| |
| ▲ | chx 2 hours ago | parent [-] | | Yeah but this is where a human is indispensable. Suppose the source language has words which could be translated into multiple English words -- look at all the power banks which are advertised as charging treasure for example. One can see how bank vs treasure are close, after all. Further, even in English multiple phrases could be used "don't preserve" "bin it" "throw it away" and countless others. Even worse, it could be a company specific phrase which would only stand out as odd "apply procedure 66 to it". If given a little thought this is exactly the kind of task where a native speaker would shine and LLM might just miss or if given a wide enough net produce a million false positive. | | |
| ▲ | infecto 2 hours ago | parent [-] | | Just tested out the treasure idea and seems to work fine in ChatGPT. I suspect if given context at the task at hand that the LLM would provide a pretty decent first pass. | | |
| ▲ | chx 39 minutes ago | parent [-] | | Y'all are hopeless. I already asked dang to delete this account. | | |
| ▲ | infecto 32 minutes ago | parent [-] | | What a weird response. Just providing a counterpoint to your idea that I don't believe is correct. I hope dang does not delete your account because I am not sure whats going on here and I hope you find the help/peace you need. | | |
| ▲ | chx 13 minutes ago | parent [-] | | I listed like half a dozen things that could go wrong and the only reply is "look this particular one in this singular case the bullshit is accidentally correct". Hopeless, as I said. | | |
| ▲ | infecto a minute ago | parent [-] | | Ouch, sorry you are in distress but let me repeat and help flesh it out for you. You would be surprised that when given the context at hand, the level of confusion would be a lot less than your constrained world model envisions. I have been pleasantly surprised with LLMs ability to translate, including legal documents. Should it be the only step in the process? No. Like I originally pointed out, I think a LLM can serve quite well in initial first passes. Its quite naive to hand wave it away with some what-if scenarios and then just become a dismissive immature kid when someone disagrees with you. I can only imagine when you have a corpus to work from of existing legal documents especially for translations, that you get quite close to the spirit of whats written. "Come delete my account dang". So childish.... |
|
|
|
|
|
|
|
| ▲ | infecto 2 hours ago | parent | prev [-] |
| You might be caught off guard then because its already happening successfully. There is a lot of overblown hype but systems already exist that do a pretty good job on first passes and other work that paralegals/juniors would be doing. I know this goes against the anti-LLM narrative here but don't be surprised as it happens. |
