Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models · HackerPapers discussions

Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models — mentioned by ijk

Mon, 06 Oct 2025 06:12:26 GMT

There's been a few attempts at training a backspace token, though. e.g.: https://arxiv.org/abs/2502.04404 https://arxiv.org/abs/2306.05426

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

Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models — mentioned by skissane

Thu, 04 Sep 2025 00:22:13 GMT

LLM backtracking is an active area of research, see e.g. https://arxiv.org/html/2502.04404v1 https://arxiv.org/abs/2306.05426 And I was wrong that nobody has implemented it, as these papers prove people have… it is just the results haven’t been sufficiently impressive to support the transition from the research lab to industrial use - or at least, not yet

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

Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models — HN submission

Mon, 10 Feb 2025 15:03:31 GMT

Self-Backtracking for Boosting Reasoning of LLMs

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