Papers › Can we obtain significant success in RST discourse parsing by using Large Language Models?

Can we obtain significant success in RST discourse parsing by using Large Language Models?

8 Mar 2024arXiv:2403.05065archive 2025-07-28

Aru Maekawa, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura

Recently, decoder-only pre-trained large language models (LLMs), with several tens of billion parameters, have significantly impacted a wide range of natural language processing (NLP) tasks. While encoder-only or encoder-decoder pre-trained language models have already proved to be effective in discourse parsing, the extent to which LLMs can perform this task remains an open research question. Therefore, this paper explores how beneficial such LLMs are for Rhetorical Structure Theory (RST) discourse parsing. Here, the parsing process for both fundamental top-down and bottom-up strategies is converted into prompts, which LLMs can work with. We employ Llama 2 and fine-tune it with QLoRA, which has fewer parameters that can be tuned. Experimental results on three benchmark datasets, RST-DT, Instr-DT, and the GUM corpus, demonstrate that Llama 2 with 70 billion parameters in the bottom-up strategy obtained state-of-the-art (SOTA) results with significant differences. Furthermore, our parsers demonstrated generalizability when evaluated on RST-DT, showing that, in spite of being trained with the GUM corpus, it obtained similar performances to those of existing parsers trained with RST-DT.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 2 code samples harvested from 1 repository linked to this paper: 0 ran · 2 unverified.

By repository: official repository: 2 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nttcslab-nlp/rstparser_eacl24 officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 2 samples, 0 ran · 2 unverified report

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

2 samples harvested: 0 ran · 2 unverified. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2unverified

Licence: 2 of the 2 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from nttcslab-nlp/rstparser_eacl24. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

nttcslab-nlp/rstparser_eacl24 official repository 2 samples, 0 ran · 2 unverified
generate_answer in 12 papers src/parse/parse_utils.py unverified licence not identified · pointer only · 01eb601638ec987f · report
split_span src/parse/top_down/parse_top_down.py unverified licence not identified · pointer only · f5d2ee40797d589c · report

Tasks

DecoderDiscourse Parsing

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Discourse Parsing RST-DT Bottom-up Llama 2 (70B) Standard Parseval (Full) 58.1 #1 of 40 Archive leaderboard report
Discourse Parsing RST-DT Bottom-up Llama 2 (70B) Standard Parseval (Nuclearity) 70.4 #1 of 40 Archive leaderboard report
Discourse Parsing RST-DT Bottom-up Llama 2 (70B) Standard Parseval (Relation) 60.0 #1 of 40 Archive leaderboard report
Discourse Parsing RST-DT Bottom-up Llama 2 (70B) Standard Parseval (Span) 79.8 #1 of 40 Archive leaderboard report
Discourse Parsing RST-DT Top-down Llama 2 (70B) Standard Parseval (Full) 56.0 #2 of 40 Archive leaderboard report
Discourse Parsing RST-DT Top-down Llama 2 (70B) Standard Parseval (Nuclearity) 68.7 #2 of 40 Archive leaderboard report
Discourse Parsing RST-DT Top-down Llama 2 (70B) Standard Parseval (Relation) 57.7 #2 of 40 Archive leaderboard report
Discourse Parsing RST-DT Top-down Llama 2 (70B) Standard Parseval (Span) 78.8 #2 of 40 Archive leaderboard report
Discourse Parsing RST-DT Bottom-up Llama 2 (13B) Standard Parseval (Full) 56.0 #3 of 40 Archive leaderboard report
Discourse Parsing RST-DT Bottom-up Llama 2 (13B) Standard Parseval (Nuclearity) 68.1 #3 of 40 Archive leaderboard report
Discourse Parsing RST-DT Bottom-up Llama 2 (13B) Standard Parseval (Relation) 57.8 #3 of 40 Archive leaderboard report
Discourse Parsing RST-DT Bottom-up Llama 2 (13B) Standard Parseval (Span) 78.3 #3 of 40 Archive leaderboard report
Discourse Parsing RST-DT Bottom-up Llama 2 (7B) Standard Parseval (Full) 55.8 #4 of 40 Archive leaderboard report
Discourse Parsing RST-DT Bottom-up Llama 2 (7B) Standard Parseval (Nuclearity) 67.5 #4 of 40 Archive leaderboard report
Discourse Parsing RST-DT Bottom-up Llama 2 (7B) Standard Parseval (Relation) 57.6 #4 of 40 Archive leaderboard report
Discourse Parsing RST-DT Bottom-up Llama 2 (7B) Standard Parseval (Span) 78.2 #4 of 40 Archive leaderboard report
Discourse Parsing RST-DT Top-down Llama 2 (13B) Standard Parseval (Full) 55.6 #6 of 40 Archive leaderboard report
Discourse Parsing RST-DT Top-down Llama 2 (13B) Standard Parseval (Nuclearity) 67.9 #6 of 40 Archive leaderboard report
Discourse Parsing RST-DT Top-down Llama 2 (13B) Standard Parseval (Relation) 57.7 #6 of 40 Archive leaderboard report
Discourse Parsing RST-DT Top-down Llama 2 (13B) Standard Parseval (Span) 78.6 #6 of 40 Archive leaderboard report
Discourse Parsing RST-DT Top-down Llama 2 (7B) Standard Parseval (Full) 53.4 #13 of 40 Archive leaderboard report
Discourse Parsing RST-DT Top-down Llama 2 (7B) Standard Parseval (Nuclearity) 65.4 #13 of 40 Archive leaderboard report
Discourse Parsing RST-DT Top-down Llama 2 (7B) Standard Parseval (Relation) 55.2 #13 of 40 Archive leaderboard report
Discourse Parsing RST-DT Top-down Llama 2 (7B) Standard Parseval (Span) 76.3 #13 of 40 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.

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