GraphWiz
Project Page: https://graph-wiz.github.io/
Paper: https://arxiv.org/abs/2402.16029.pdf
Code: https://github.com/nuochenpku/Graph-Reasoning-LLM
GraphWiz is a powerful instruction-following LLM that can map textural descriptions of graphs and structures, and then solve different graph problems explicitly in natural language.
Training strategies include two stages: Mixed-task Training and DPO Alignment.
Results
Models | Cycle | Connect | Bipartite | Topology | Shortest | Triangle | Flow | Hamilton | Subgraph | Average |
---|---|---|---|---|---|---|---|---|---|---|
In-Context Learning | ||||||||||
GPT-4 (zero-shot) | 38.75 | 17.00 | 65.25 | 5.00 | 9.25 | 5.75 | 3.25 | 59.25 | 45.50 | 27.67 |
GhatGPT (2-shot) | 51.25 | 43.75 | 70.75 | 4.50 | 3.50 | 17.25 | 8.50 | 54.25 | 43.00 | 32.97 |
GPT-4 (2-shot) | 52.50 | 62.75 | 74.25 | 25.25 | 18.25 | 31.00 | 7.75 | {75.75} | 46.75 | 43.81 |
Mistral-7B | ||||||||||
Naive SFT | 73.75 | 83.50 | 78.50 | 1.00 | 23.00 | 47.00 | 28.75 | 31.75 | 41.25 | 46.56 |
GraphWiz | 92.00 | 89.50 | 72.00 | 19.00 | 31.25 | 38.75 | 29.25 | 26.50 | 85.50 | 53.75 |
GraphWiz-DPO | 85.50 | 79.50 | 85.50 | 85.25 | 12.50 | 29.00 | 35.50 | 62.75 | 48.50 | 58.22 |
LLaMA 2-7B | ||||||||||
Naive SFT | 73.75 | 83.50 | 41.25 | 4.00 | 9.50 | 30.00 | 16.50 | 69.00 | 75.45 | 44.81 |
GraphWiz | 91.50 | 87.00 | 74.00 | 18.00 | 28.00 | 38.25 | 24.50 | 52.25 | 82.25 | 55.08 |
GraphWiz-DPO | 89.00 | 82.50 | 84.75 | 46.75 | 24.00 | 52.75 | 43.50 | 81.50 | 77.25 | 65.00 |
LLaMA 2-13B | ||||||||||
Naive SFT | 73.75 | 83.75 | 59.00 | 0.50 | 11.75 | 34.75 | 24.25 | 59.75 | 54.75 | 44.69 |
GraphWiz | 94.75 | 87.00 | 78.00 | 28.00 | 27.75 | 36.00 | 24.50 | 59.00 | 81.50 | 57.39 |
GraphWiz-DPO | 87.50 | 88.50 | 88.25 | 72.75 | 22.00 | 48.75 | 43.75 | 46.50 | 77.00 | 63.89 |
Examples
G-Q: Determine whether or not there is a cycle in an undirected graph. In an undirected graph..,the
nodes are numbered from 0 to 88, and the edges are: (0, 73) (0, 51) (0, 10) (0, 63) (0, 28) (1, 62) (1, 57) (1, 84) (1, 61) (1, 5)
(1, 24) (2, 84) (2, 3) (2, 66) (2, 68) (2, 17) (2, 35) (2, 34) (2, 15) (3, 39) (3, 52) (3, 16) (3, 15) (3, 8) (4, 69) (4, 85)
(4, 36) (4, 72) (5, 44) (6, 77) (6, 7) (7, 85) (8, 64) (8, 23) (8, 28) (9, 34) (9, 31) (9, 61) (9, 28) (10, 26) (11, 37) (11, 39)
(11, 19) (11, 64) (13, 73) (13, 61) (13, 80) (13, 85) (14, 86) (14, 59) (14, 32) (14, 58) (14, 85) (14, 66) (15, 43) (15, 48) (15, 73)
(15, 19) (15, 47) (15, 68) (16, 46) (16, 60) (16, 84) (17, 44) (17, 72) (17, 36) (17, 37) (17, 61) (18, 20) (18, 24) (18, 22) (18, 41)
(19, 45) (19, 83) (20, 25) (20, 29) (21, 38) (21, 64) (21, 24) (21, 22) (21, 34) (22, 23) (23, 34) (23, 30) (23, 83) (24, 47) (24, 50)
(25, 59) (25, 42) (25, 70) (25, 72) (26, 45) (26, 30) (26, 87) (26, 80) (26, 50) (27, 77) (27, 58) (27, 60) (27, 29) (28, 36) (28, 59)
(28, 88) (29, 31) (29, 33) (29, 56) (29, 55) (29, 78) (29, 73) (29, 82) (30, 34) (31, 58) (31, 70) (32, 78) (33, 73) (33, 68) (34, 48)
(34, 88) (34, 51) (34, 66) (34, 54) (35, 43) (35, 56) (36, 44) (36, 39) (37, 57) (37, 71) (38, 47) (38, 58) (38, 88) (39, 74) (39, 48)
(39, 45) (39, 42) (40, 60) (40, 59) (40, 71) (40, 76) (41, 79) (42, 60) (42, 62) (42, 72) (43, 57) (44, 47) (44, 74) (44, 75) (44, 82)
(44, 70) (45, 68) (45, 67) (45, 71) (46, 84) (47, 56) (48, 75) (49, 71) (49, 58) (50, 76) (51, 55) (51, 87) (51, 79) (52, 78) (56, 69)
(56, 83) (56, 79) (57, 76) (57, 70) (57, 72) (57, 78) (59, 70) (60, 80) (60, 76) (60, 77) (60, 75) (61, 74) (61, 77) (62, 84) (62, 66)
(66, 69) (68, 88) (70, 88) (70, 76) (71, 81) (71, 72) (71, 86) (72, 75) (73, 82) (73, 83) (74, 85). Is there a cycle in this graph?
GraphWiz:
There are many possible ways to find a cycle in this graph, but one example is: Starting from node 0, we can go to node 73 (via edge 0-73), then to node 82 (via edge 73-82),
then to node 44 (via edge 82-44), then to node 17 (via edge 44-17), then to node 36 (via edge 17-36), then to node 28 (via edge 36-28),
and back to node 0 (via edge 28-0). This forms a cycle [0-73-82-44-17-36-28-0] without revisiting any edge. So, there is a cycle in this graph.
- Downloads last month
- 522
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.