Papers › PALM: Pre-training an Autoencoding&Autoregressive Language Model for...
PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation
Bin Bi, Chenliang Li, Chen Wu, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, Luo Si
Self-supervised pre-training, such as BERT, MASS and BART, has emerged as a powerful technique for natural language understanding and generation. Existing pre-training techniques employ autoencoding and/or autoregressive objectives to train Transformer-based models by recovering original word tokens from corrupted text with some masked tokens. The training goals of existing techniques are often inconsistent with the goals of many language generation tasks, such as generative question answering and conversational response generation, for producing new text given context. This work presents PALM with a novel scheme that jointly pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus, specifically designed for generating new text conditioned on context. The new scheme alleviates the mismatch introduced by the existing denoising scheme between pre-training and fine-tuning where generation is more than reconstructing original text. An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks covering generative question answering (Rank 1 on the official MARCO leaderboard), abstractive summarization on CNN/DailyMail as well as Gigaword, question generation on SQuAD, and conversational response generation on Cornell Movie Dialogues.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Abstractive Text Summarization | CNN / Daily Mail | PALM | ROUGE-1 | 44.30 | #16 of 53 | Archive leaderboard | report |
| Abstractive Text Summarization | CNN / Daily Mail | PALM | ROUGE-2 | 21.12 | #16 of 53 | Archive leaderboard | report |
| Abstractive Text Summarization | CNN / Daily Mail | PALM | ROUGE-L | 41.41 | #16 of 53 | Archive leaderboard | report |
| Text Generation | CNN/Daily Mail | PALM | ROUGE-L | 41.41 | #1 of 1 | Archive leaderboard | report |
| Text Summarization | GigaWord | PALM | ROUGE-1 | 39.45 | #11 of 41 | Archive leaderboard | report |
| Text Summarization | GigaWord | PALM | ROUGE-2 | 20.37 | #11 of 41 | Archive leaderboard | report |
| Text Summarization | GigaWord | PALM | ROUGE-L | 36.75 | #11 of 41 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections