TREC 2025 Proceedings

grilllab-larf-finetuned

Submission Details

Organization
grilllab
Track
Interactive Knowledge Acquisition Track
Task
Passage Ranking and Response Generation
Date
2025-07-26

Run Description

What type of manually annotated information does the system use?
automatic: system does not use any manually annotated data and relies only on the user utterance and system responses (canonical responses of previous turns)
How is conversation understanding (NLP/rewriting) performed in this run (check all that apply)?
['method uses large language models like LLaMA and GPT-x.']
What data is used for conversational query understanding in this run (check all that apply)?
['method uses iKAT 23 data', 'method uses data provided from CAsT datasets']
How is ranking performed in this run (check all that apply)?
['method uses traditional unsupervised sparse retrieval (e.g.¸ QL¸ BM25¸ etc.)', 'method uses document expansion (e.g.¸ Doc2Query)', 'method performs re-ranking with a pre-trained neural language model (BERT¸ Roberta¸ T5¸ etc.) (please describe specifics in the description field below)', 'method performs re-ranking with large langauge models (LLaMA¸ GPT-x¸ etc.) (please describe specifics in the description field below)']
What data is used to develop the ranking method in this run (check all that apply)?
['method is trained with CAsT datasets', 'method uses iKAT 23 data']
Please specify all the methods used to handle feedback or clarification responses from the user (check all that apply).
['method does not treat them specially']
Please describe the method used to generate the final conversational responses from one or more retrieved passages (check all that apply).
['method uses large language models to generate the summary.']
Please describe how you integrate the PTKBs in your run (check all that apply)
[' method uses a PTKB relevance model to detect the relevant ones', " method integrates PTKBs in the response generation method (e.g. include in the LLM's prompt)"]
Which LLM did you use to generate the final response?
['method uses closed-source commercial LLMs (e.g. GPT-*)']
Please describe the external resources used by this run, if applicable.
CAsT 2022 and iKAT 2023 data
Please provide a short description of this run.
There are three stages to this run: - A candidate passage generation stage where the system rewrites the user's query in the context of the conversation and PTKBs, then retrieves 500 documents from the collection using BM25. - An expansion phase where the system uses existing documents to find similar documents from the collection with BM25. - A refinement phase where an LLM analyses the candidate passages and synthesises new queries to find more passages that address any gaps found Each phase consists of a passage filtering and reranking step. The output of each stage is a ranked list that is then fed to the next stage. Responses are generated with an LLM
Please provide a priority for assessing this run. (If resources do not allow all runs to be assessed, NIST will work in priority order, resolving ties arbitrarily).
1 (top)

Evaluation Files

Paper