Papers › Efficient Dynamic Hard Negative Sampling for Dialogue Selection
Efficient Dynamic Hard Negative Sampling for Dialogue Selection
Janghoon Han, Dongkyu Lee, Joongbo Shin, Hyunkyung Bae, Jeesoo Bang, SeongHwan Kim, Stanley Jungkyu Choi, and Honglak Lee.
Recent studies have demonstrated significant improvements in selection tasks, and a considerable portion of this success is attributed to incorporating informative negative samples during training. While traditional methods for constructing hard negatives provide meaningful supervision, they depend on static samples that do not evolve during training, leading to sub-optimal performance. Dynamic hard negative sampling addresses this limitation by continuously adapting to the model’s changing state throughout training. However, the high computational demands of this method restrict its applicability to certain model architectures. To overcome these challenges, we introduce an efficient dynamic hard negative sampling (EDHNS). EDHNS enhances efficiency by pre-filtering easily discriminable negatives, thereby reducing the number of candidates the model needs to compute during training. Additionally, it excludes question-candidate pairs where the model already exhibits high confidence from loss computations, further reducing training time. These approaches maintain learning quality while minimizing computation and streamlining the training process. Extensive experiments on DSTC9, DSTC10, Ubuntu, and E-commerce benchmarks demonstrate that EDHNS significantly outperforms baseline models, proving its effectiveness in dialogue selection tasks.
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 |
|---|---|---|---|---|---|---|---|
| Conversational Response Selection | E-commerce | BERT-FP+EDHNS | R10@1 | 0.957 | #1 of 15 | Archive leaderboard | report |
| Conversational Response Selection | E-commerce | BERT-FP+EDHNS | R10@2 | 0.986 | #1 of 15 | Archive leaderboard | report |
| Conversational Response Selection | E-commerce | BERT-FP+EDHNS | R10@5 | 0.997 | #1 of 15 | Archive leaderboard | report |
| Conversational Response Selection | Ubuntu Dialogue (v1, Ranking) | BERT-FP+EDHNS | R10@1 | 0.917 | #2 of 25 | Archive leaderboard | report |
| Conversational Response Selection | Ubuntu Dialogue (v1, Ranking) | BERT-FP+EDHNS | R10@2 | 0.965 | #2 of 25 | Archive leaderboard | report |
| Conversational Response Selection | Ubuntu Dialogue (v1, Ranking) | BERT-FP+EDHNS | R10@5 | 0.994 | #2 of 25 | 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